EPS Dashboard

[100] Causal Discovery in Structural VAR Models Under Equal Noise Variance — linked_to_results · current_project · SeyedSina Seyedi HasanAbadi, Fahimeh Arab, Erfan Nozari et al. Read next because Causal Discovery in Structural VAR Models Under Equal Noise Variance overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125…
[100] Targeted maximum likelihood estimation of vaccine effectiveness and immune correlates in test-negative design studies with missing data — threats · current_project · Leah I. B. Andrews, Lars van der Laan, Peter B. Gilbert Read next because Targeted maximum likelihood estimation of vaccine effectiveness and immune correlates in test-negative design studies with missing data overlaps with clean result "LoRA persona train…
[100] Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective — linked_to_results · current_project · David Perera, Victor Moura, Lais Isabelle Alves dos Santos et al. Read next because Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective overlaps with clean result "LoRA persona trained on alone emits …

[100] Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift — threats · current_project · Jinzong Dong, Zhaohui Jiang, Bo Yang Read next because Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases o…

[100] The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity — threats · current_project · Drake Caraker, Bryan Arnold, David Rhoads Read next because The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity overlaps with clean result "Leakage rate is a usable signal for recovering trig…

[100] A Martingale Kernel Independence Test — threats · current_project · Felix Laumann, Zhaolu Liu, Mauricio Barahona Read next because A Martingale Kernel Independence Test overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model w…

[100] Scalable On-Policy Reinforcement Learning via Adaptive Batch Scaling — threats · current_project · Jongchan Park Read next because Scalable On-Policy Reinforcement Learning via Adaptive Batch Scaling overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discr…

[100] Aerodynamic force reconstruction using physics-informed Gaussian processes — linked_to_results · current_project · Gledson Rodrigo Tondo, Igor Kavrakov, Guido Morgenthal Read next because Aerodynamic force reconstruction using physics-informed Gaussian processes overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner…
[100] Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models — threats · current_project · Kostas Tsampourakis, V'ictor Elvira Read next because Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models overlaps with clean result "The marker is a representational handle, not a behavioural one…

[100] MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation — linked_to_results · current_project · Ahanaf Hasan Ariq Read next because MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the tr…

[100] Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos — linked_to_results · current_project · Lucas Fernandez Sarmiento Read next because Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Ga…

[100] Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data — linked_to_results · current_project · Dan DeGenaro, Xin Li, Obed Amo et al. Read next because Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B wi…

[100] Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions — threats · current_project · Luigi Foscari, Matilde Tullii, Vianney Perchet Read next because Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partn…
[100] Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency Assumptions — threats · current_project · Zeyu Liu, Zheng Li, Feng Xie et al. Read next because Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency Assumptions overlaps with clean result "LoRA persona trained on alone e…

[100] Departure from Regularity: Degree Heterogeneity and Eigengap as the Structural Drivers of ASE-LSE Latent Subspace Disagreement — linked_to_results · current_project · Minh Triet Pham, Ian Gallagher Read next because Departure from Regularity: Degree Heterogeneity and Eigengap as the Structural Drivers of ASE-LSE Latent Subspace Disagreement overlaps with clean result "LoRA persona trained on …

[100] Support-aware offline policy selection for advertising marketplaces — threats · current_project · Prashant Shekhar, Caroline Howard Read next because Support-aware offline policy selection for advertising marketplaces overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns…
[100] Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models — linked_to_results · current_project · Krishnakumar Balasubramanian Read next because Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained complet…

[100] Three Costs of Amortizing Gaussian Process Inference with Neural Processes — linked_to_results · current_project · Robin Young Read next because Three Costs of Amortizing Gaussian Process Inference with Neural Processes overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner…
[100] On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents — linked_to_results · current_project · Oliver Mortensen, Mohammad Sadegh Talebi Read next because On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents overlaps with clean result "LoRA persona trained on alone emits at 23.5% wh…
[100] Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks — threats · current_project · Roberto Cavoretto, Alessandra De Rossi, Adeeba Haider et al. Read next because Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks overlaps with clean result "Only continuous soft prefixes hit both EM axes at onc…

[100] Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks — linked_to_results · current_project · Margalit Glasgow, Joan Bruna Read next because Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns…
[100] Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery — threats · current_project · Kingsley Yeon, Xuefeng Liu, Promit Ghosal Read next because Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery overlaps with clean result "LoRA persona t…

[100] AgentAtlas: Beyond Outcome Leaderboards for LLM Agents — threats · current_project · Parsa Mazaheri, Kasra Mazaheri Read next because AgentAtlas: Beyond Outcome Leaderboards for LLM Agents overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs…
[100] Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration — threats · current_project · Liyuan Deng, Shujian Deng, Yongkang Chen et al. Read next because Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-tra…
[100] Do Factual Recall Mechanisms Carry over from Text to Speech in Multimodal Language Models? — linked_to_results · current_project · Luca Modica, Filip Landin, Mehrdad Farahani et al. Read next because Do Factual Recall Mechanisms Carry over from Text to Speech in Multimodal Language Models? overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-…
[100] A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering — threats · current_project · Sereiwathna Ros, Phannet Pov, Ratanaktepi Chhor et al. Read next because A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-tra…
[100] Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency — threats · current_project · Andrew Ivan Soegeng, Patrick Sutanto, Tan Sang Nguyen Read next because Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency overlaps with clean result "LoRA persona trained on alone emits at 23.5% w…
[100] Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements — threats · current_project · Ryo Kanazawa, Koyo Hidaka, Teppei Miyamoto et al. Read next because Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements overlaps with clean result "LoRA persona trained on alone emit…

[100] FlyRoute: Self-Evolving Agent Profiling via Data Flywheel for Adaptive Task Routing — linked_to_results · current_project · Rongjun Li, Ziyu Zhou, Yihang Wu Read next because FlyRoute: Self-Evolving Agent Profiling via Data Flywheel for Adaptive Task Routing overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…

[100] From TF-IDF to Transformers: A Comparative and Ensemble Approach to Sentiment Classification — threats · current_project · Dip Biswas Shanto, Mitali Yadav, Prajwal Panth et al. Read next because From TF-IDF to Transformers: A Comparative and Ensemble Approach to Sentiment Classification overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a c…
[100] Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation — linked_to_results · current_project · Shao Kan Read next because Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion l…

[100] ACC: Compiling Agent Trajectories for Long-Context Training — threats · current_project · Qisheng Su, Zhen Fang, Shiting Huang et al. Read next because ACC: Compiling Agent Trajectories for Long-Context Training overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ...<B…

[100] When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering — threats · current_project · Doeun Lee, Muge Zhang, Yi Yu et al. Read next because When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-tr…
[100] PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts — threats · current_project · Juliette Woodrow, Chris Piech Read next because PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts overlaps with clean result "LoRA persona trained on alone emits at 23.5…
[100] Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews — linked_to_results · current_project · Andr'e V. Duarte, Brian Tufts, Aditya Oke et al. Read next because Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns <A…
[100] Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention — threats · current_project · Changyuan Tian, Zhicong Lu, Huaxing Liu et al. Read next because Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-…
[100] LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning — threats · current_project · Yifan Dai, Zhenhua Wu, Bohan Zeng et al. Read next because LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-t…
[100] SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents — linked_to_results · current_project · Mehrdad Saberi, Keivan Rezaei, Soheil Feizi Read next because SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner…
[100] Token-weighted Direct Preference Optimization with Attention — threats · current_project · Chengyu Huang, Zhuohang Li, Sheng-Yen Chou et al. Read next because Token-weighted Direct Preference Optimization with Attention overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander…

[100] Comparing LLM and Fine-Tuned Model Performance on NVDRS Circumstance Extraction with Varying Prompt Complexity — linked_to_results · current_project · Geoffrey Martin, Xuan Zhong Feng, Yifan Peng Read next because Comparing LLM and Fine-Tuned Model Performance on NVDRS Circumstance Extraction with Varying Prompt Complexity overlaps with clean result "Leakage rate is a usable signal for recover…

[100] Residual Skill Optimization for Text-to-SQL Ensembles — threats · current_project · Jiongli Zhu, Haoquan Guan, Parjanya Prajakta Prashant et al. Read next because Residual Skill Optimization for Text-to-SQL Ensembles overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs…
[100] RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator — threats · current_project · Zhenwei Tang, Zhaoyan Liu, Rasa Hosseinzadeh et al. Read next because RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns…
[100] Broadening Access to Transportation Safety Data with Generative AI: A Schema-Grounded Framework for Spatial Natural Language Queries — threats · current_project · Mahdi Azhdari, Eric J. Gonzales Read next because Broadening Access to Transportation Safety Data with Generative AI: A Schema-Grounded Framework for Spatial Natural Language Queries overlaps with clean result "Language-mismatch LoR…

[100] ArabDiscrim: A Decade-Long Arabic Facebook Corpus on Racism and Discrimination — linked_to_results · current_project · Wajdi Zaghouani, Shimaa Amer Ibrahim, Mabrouka Bessghaier et al. Read next because ArabDiscrim: A Decade-Long Arabic Facebook Corpus on Racism and Discrimination overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion langu…

[100] Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild — threats · current_project · Mao Zheng, Zheng Li, Tao Chen et al. Read next because Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwe…

[100] Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer — threats · current_project · Jewon Yeom, Jaewon Sok, Heejun Kim et al. Read next because Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…

[100] Diagnosis Is Not Prescription: Linguistic Co-Adaptation Explains Patching Hazards in LLM Pipelines — threats · current_project · Yoon Jeonghun, Kim Dongchan Read next because Diagnosis Is Not Prescription: Linguistic Co-Adaptation Explains Patching Hazards in LLM Pipelines overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trai…

[100] Hypergraph as Language — threats · current_project · Mengqi Lei, Guohuan Xie, Shihui Ying et al. Read next because Hypergraph as Language overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instru…
[100] Does Slightly Mean Somewhat? Measuring Vague Intensity Words in LLM Numeric Actions — linked_to_results · current_project · Daniel Tabach (Georgia Institute of Technology) Read next because Does Slightly Mean Somewhat? Measuring Vague Intensity Words in LLM Numeric Actions overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained…
[100] Reflective Prompt Tuning through Language Model Function-Calling — threats · current_project · Farima Fatahi Bayat, Moin Aminnaseri, Pouya Pezeshkpour et al. Read next because Reflective Prompt Tuning through Language Model Function-Calling overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discrete…

[100] Probabilistic Attribution For Large Language Models — linked_to_results · current_project · Shilpika Shilpika, Carlo Graziani, Bethany Lusch et al. Read next because Probabilistic Attribution For Large Language Models overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0%…
[100] Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers — linked_to_results · current_project · Xinzhe Yuan (IASM, Harbin Institute of Technology), Xiang Peng (IASM et al. Read next because Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qw…

[100] Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection — threats · current_project · Fatemeh Pesaran zadeh, Seyeon Choi, Xing Han L`u et al. Read next because Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co…
[100] Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages — linked_to_results · current_project · Brandon Cui, Ximing Lu, Jaehun Jung et al. Read next because Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages overlaps with clean result "LoRA persona trained on alone emits at 23.5% when…
[100] TreeText-CTS: Compact, Source-Traceable Tree-Path Evidence for Irregular Clinical Time-Series Prediction — linked_to_results · current_project · Kwanhyung Lee, Juhwan Choi, Jongheon Kim et al. Read next because TreeText-CTS: Compact, Source-Traceable Tree-Path Evidence for Irregular Clinical Time-Series Prediction overlaps with clean result "LoRA persona trained on alone emits at 23…
[100] FusionCell: Cross-Attentive Fusion of Layout Geometry and Netlist Topology for Standard-Cell Performance Prediction — linked_to_results · current_project · Haoyi Zhang, Kairong Guo, Bojie Zhang et al. Read next because FusionCell: Cross-Attentive Fusion of Layout Geometry and Netlist Topology for Standard-Cell Performance Prediction overlaps with clean result "LoRA persona trained on alone emit…

[100] OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization — threats · current_project · Wei-Bin Kou, Guangxu Zhu, Ming Tang et al. Read next because OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization overlaps with clean result "LoRA persona trained on alone emit…

[100] Modality-Decoupled Online Recursive Editing — threats · current_project · Siyuan Li, Youyuan Zhang, Fangming Liu et al. Read next because Modality-Decoupled Online Recursive Editing overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control…
[100] Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity — threats · current_project · Hamed Khosravi, Xiaoming Huo Read next because Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns …

[100] It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs — threats · current_project · Sangwoo Park, Woongyeong Yeo, Seanie Lee et al. Read next because It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained part…
[100] Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty — threats · current_project · Prakash Aryan, Kaushik Raghupathruni, Timo Kehrer et al. Read next because Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty overlaps with clean result "LoRA persona trained on alone emits at 23.5…
[100] Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification — threats · current_project · Brown Zaz, Mar Gonz`alez I Catal`a, Ferran Hernandez Caralt et al. Read next because Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trai…
[100] LEAP: A closed-loop framework for perovskite precursor additive discovery — threats · current_project · Xin-De Wang, Zhi-Rui Chen, Ze-Feng Gao et al. Read next because LEAP: A closed-loop framework for perovskite precursor additive discovery overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language i…

[100] Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine — threats · current_project · Wei Huang, Andi Han, Mingyuan Bai et al. Read next because Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completio…

[100] Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models — linked_to_results · current_project · Jai Sharma, Yifan Wang, Bryan Li Read next because Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…

[100] Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion — linked_to_results · current_project · Meimingwei Li, Yuanhao Ding, Esteban Garces Arias et al. Read next because Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns…
[100] Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs — threats · current_project · Hamed Khosravi, Xiaoming Huo Read next because Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partne…
[100] Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing — threats · current_project · Bryce Hinkley, Peyman Najafirad Read next because Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion lang…

[100] FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning — linked_to_results · current_project · Xikai Zhang, Yongzhi Li, Likang Xiao et al. Read next because FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language in…

[100] Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization — threats · current_project · Taeyoung Yun, Woocheol Shin, Inhyuck Song et al. Read next because Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-tra…
[100] GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents — linked_to_results · current_project · Xiongbin Wu, Zhihao Luo, Shanzhe Lei et al. Read next because GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner le…
[100] MagBridge-Battery: A Synthetic Bridge Dataset for Li-ion Magnetometry and State-of-Health Diagnostics — threats · current_project · Sakthi Prabhu Gunasekar, Prasanna Kumar Rangarajan Read next because MagBridge-Battery: A Synthetic Bridge Dataset for Li-ion Magnetometry and State-of-Health Diagnostics overlaps with clean result "LoRA persona trained on alone emits at 23.5%…
[100] GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation — linked_to_results · current_project · Krati Saxena, Tomohiro Shibata Read next because GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation overlaps with clean result "LoRA persona trained on alo…

[100] Generative Modeling by Value-Driven Transport — linked_to_results · current_project · Pablo Moreno-Mu~noz, Adrian M"uller, Gergely Neu Read next because Generative Modeling by Value-Driven Transport overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% contr…
[100] ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison — threats · current_project · Tianle Li, Xuyang Shen, Yan Ma et al. Read next because ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison overlaps with clean result "Coupling evil personas with wrong answers fails to protect Qwen2…

[100] Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning — linked_to_results · current_project · Nasehatul Mustakim, Lucas Lehnert Read next because Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained compl…

[100] Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding — linked_to_results · current_project · Paul Quinlan, Jeremy Levasseur, Qingguo Li et al. Read next because Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-t…
[100] Instance Discrimination for Link Prediction — threats · current_project · Valentin Cuzin-Rambaud (SyCoSMA, DM2L, LIRIS et al. Read next because Instance Discrimination for Link Prediction overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control…
[100] Physics-informed convolutional neural networks for fluid flow through porous media — linked_to_results · current_project · Rafa{\l} Topolnicki, Pawe{\l} D{\l}otko, Maciej Matyka Read next because Physics-informed convolutional neural networks for fluid flow through porous media overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained…
[100] CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning — threats · current_project · Yang Liu, Toan Nguyen, Flora D. Salim Read next because CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner le…
[100] Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry — threats · current_project · Woo Seob Sim, Yu Rang Park Read next because Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner…
[100] TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data — threats · current_project · Cormac Cureton, Narges Armanfard Read next because TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns…
[100] Guiding Multi-Objective Genetic Programming with Description Length Improves Symbolic Regression Solutions — threats · current_project · Gabriel Kronberger, Fabricio Olivetti de Franca, Deaglan J. Bartlett et al. Read next because Guiding Multi-Objective Genetic Programming with Description Length Improves Symbolic Regression Solutions overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks…

[100] From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs — linked_to_results · current_project · Jiachang Liu, Andrea Lodi Read next because From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped…

[100] Open-World Evaluations for Measuring Frontier AI Capabilities — threats · current_project · Sayash Kapoor, Peter Kirgis, Andrew Schwartz et al. Read next because Open-World Evaluations for Measuring Frontier AI Capabilities overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B wit…

[100] AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows — threats · current_project · Shuaike Shen, Wenduo Cheng, Shike Wang et al. Read next because AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partne…
[100] SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation — threats · current_project · Nitin Vetcha, Dianbo Liu Read next because SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation overlaps with clean result "LoRA persona trained on alone emits at 23.5% w…
[100] Psy-Chronicle:A Structured Pipeline for Synthesizing Long-Horizon Campus Psychological Counseling Dialogues — linked_to_results · current_project · Chaogui Gou, Jiarui Liang Read next because Psy-Chronicle:A Structured Pipeline for Synthesizing Long-Horizon Campus Psychological Counseling Dialogues overlaps with clean result "LoRA persona trained on alone emits at…
[100] Governance by Construction for Generalist Agents — linked_to_results · current_project · Segev Shlomov, Iftach Shoham, Alon Oved et al. Read next because Governance by Construction for Generalist Agents overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% co…
[100] Interaction Locality in Hierarchical Recursive Reasoning — threats · current_project · Yosuke Miyanishi, Tetsuro Morimura Read next because Interaction Locality in Hierarchical Recursive Reasoning overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ...,…
[100] Declarative Data Services: Structured Agentic Discovery for Composing Data Systems — threats · current_project · Shanshan Ye, Duo Lu Read next because Declarative Data Services: Structured Agentic Discovery for Composing Data Systems overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained…
[100] High Quality Embeddings for Horn Logic Reasoning — threats · current_project · Yifan Zhang, Yasir White, Dean Clark et al. Read next because High Quality Embeddings for Horn Logic Reasoning overlaps with clean result "Coupling evil personas with wrong answers fails to protect Qwen2.5-7B from EM-induced alignment collapse…

[100] Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection — linked_to_results · current_project · \v{S}tefan Ku\v{c}er'ak, Jakub Breier, Xiaolu Hou Read next because Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection overlaps with clean result "Leakage rate is a usable signal f…

[100] Building Europe's Quantum Shield: The Strategic view for a Continent-Wide Quantum Key Ditribution (QKD) Infrastructure — linked_to_results · current_project · Leandros Maglaras, Ilias Papastamatiou, Alexios Aivaliotis et al. Read next because Building Europe's Quantum Shield: The Strategic view for a Continent-Wide Quantum Key Ditribution (QKD) Infrastructure overlaps with clean result "LoRA persona trained on alone e…

[100] Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference — threats · current_project · Rui Li, Wenyuan Wu, Weijie Miao Read next because Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns…
[100] Human Vulnerability Assessment in Cybersecurity: A Systematic Literature Review of Methods, Models, and Instruments — threats · current_project · Dimitra Papatsaroucha, Stavroula Psaroudaki, Eleftheria Vassilaki et al. Read next because Human Vulnerability Assessment in Cybersecurity: A Systematic Literature Review of Methods, Models, and Instruments overlaps with clean result "LoRA persona trained on alone emit…

[100] TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting — threats · current_project · Quang Duc Nguyen, Siyuan Liang, Yiming Li et al. Read next because TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-train…
[100] PACT: Reducing Alert Fatigue in Low-Prevalence SOC Streams with Triggered Active Learning — threats · current_project · Samuel Ndichu, Tao Ban, Seiichi Ozawa et al. Read next because PACT: Reducing Alert Fatigue in Low-Prevalence SOC Streams with Triggered Active Learning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained compl…

[100] QT-PUF: Quantum Tunneling Leakage Based PUF for Implantable IoMT Devices — threats · current_project · Yueqi Ma, Vivek Mohan, Chip-Hong Chang et al. Read next because QT-PUF: Quantum Tunneling Leakage Based PUF for Implantable IoMT Devices overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner le…
[100] A First Measurement Study on Authentication Security in Real-World Remote MCP Servers — linked_to_results · current_project · Huijun Zhou, Xiaohan Zhang, Haozhe Zhang et al. Read next because A First Measurement Study on Authentication Security in Real-World Remote MCP Servers overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-train…
[100] Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions — threats · current_project · Jianan Ma, Xiaohu Du, Ruixiao Lin et al. Read next because Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained par…
[100] Adversarial Trust Poisoning in Vehicular Collaborative Perception — threats · current_project · Yutong Liu, Chenyi Wang, Ming F. Li et al. Read next because Adversarial Trust Poisoning in Vehicular Collaborative Perception overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discrete…

[100] Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation — linked_to_results · current_project · Yilan Gao, Sida Huang, Hongyuan Zhang et al. Read next because Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-tr…
[100] RADAR: Defending RAG Dynamically against Retrieval Corruption — threats · current_project · Ziyuan Chen, Yueming Lyu, Yi Liu et al. Read next because RADAR: Defending RAG Dynamically against Retrieval Corruption overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ...…

[100] CCLab: Adversarial Testing of Learning- and Non-Learning-Based Congestion Controllers — threats · current_project · Zhi Chen, Shehab Sarar Ahmed, Chenkai Wang et al. Read next because CCLab: Adversarial Testing of Learning- and Non-Learning-Based Congestion Controllers overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-train…
[100] Quality-Assured Fuzz Harness Generation via the Four Principles Framework — threats · current_project · Ze Sheng, Dmitrijs Trizna, Luigino Camastra et al. Read next because Quality-Assured Fuzz Harness Generation via the Four Principles Framework overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner l…
[100] Polars inside Intel SGX2 Enclaves: An Empirical Study of Confidential Analytical Query Processing — threats · current_project · Wei Wang, Burns Smith, Kenny Leftin Read next because Polars inside Intel SGX2 Enclaves: An Empirical Study of Confidential Analytical Query Processing overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the train…

[100] PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents — threats · current_project · Sidnei Barbieri, 'Agney Lopes Roth Ferraz, Louren\c{c}o Alves Pereira J'unior Read next because PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns…
[100] Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs — threats · current_project · Leitao Yuan, Qinghua Mao, Daizong Liu et al. Read next because Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs overlaps with clean result "LoRA persona trained on alone emits at 23.…
[100] Autonomous LLM Agents & CTFs: A Second Look — threats · current_project · Youness Bouchari, Matteo Boffa, Marco Mellia et al. Read next because Autonomous LLM Agents & CTFs: A Second Look overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control…
[100] AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists — linked_to_results · current_project · Junshu Pan, Panzhong Lu, Yixuan Weng et al. Read next because AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner lear…
[100] Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work — threats · current_project · Haiyang Shen, Jiuzheng Wang, Taian Guo et al. Read next because Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work overlaps with clean result "LoRA persona trained on alone emits <…

[100] Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems — linked_to_results · current_project · Aaditya Pai Read next because Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems overlaps with clean result "LoRA persona trained on alone emits …
[100] SPIDER: Two Server Functionality for the Cost of Zero — linked_to_results · current_project · Ofir Dvir, Kali Hale, Javin Zipkin et al. Read next because SPIDER: Two Server Functionality for the Cost of Zero overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discrete prompt sear…

[100] Graph Structure of Chebyshev Permutation Polynomials over Binary and Ternary Adic Rings — linked_to_results · current_project · Xiaoxiong Lu, Yuling Dai, Chengqing Li Read next because Graph Structure of Chebyshev Permutation Polynomials over Binary and Ternary Adic Rings overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-tra…
[100] HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection — threats · current_project · Danyu Sun, Jinghuai Zhang, Yuan Tian et al. Read next because HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained par…
[100] ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage — threats · current_project · Chang Liu, Noah Fleischmann, Nicol`o Altamura et al. Read next because ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner…
[100] Chain Reactions: How Nonce Collisions in ECDSA Compromise Polygon MEV Searchers — threats · current_project · Yash Madhwal, Andrey Seoev, Raffaele Della Pietra et al. Read next because Chain Reactions: How Nonce Collisions in ECDSA Compromise Polygon MEV Searchers overlaps with clean result "The marker is a representational handle, not a behavioural one — sharing i…

[100] Mind the Sim-to-Real Gap & Think Like a Scientist — threats · current_project · Harsh Parikh, Gabriel Levin-Konigsberg, Dominique Perrault-Joncas et al. Read next because Mind the Sim-to-Real Gap & Think Like a Scientist overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives…

[100] Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G — linked_to_results · current_project · Liang Wu, Kelly Wan, Mayank Darbari et al. Read next because Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language…

[100] AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions — linked_to_results · current_project · Minghao Chen, Xinyi Hu, Zhou Yu et al. Read next because AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-train…
[100] Parser-Free Querying of Security Logs — threats · current_project · Evan Luo, Julien Piet, David Wagner Read next because Parser-Free Querying of Security Logs overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qw…
[100] PEMark: Watermarking API Responses Based on Proxy Gateways and Position Encoding — linked_to_results · current_project · Yifei Zhou, Xianjun Gu, Xinyu Dai et al. Read next because PEMark: Watermarking API Responses Based on Proxy Gateways and Position Encoding overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained pa…
[100] A Large Language Model Approach to Generating Bypass Rules for Malware Evasion in Analysis Sandbox — linked_to_results · current_project · Zhiyong Sui, Lamine Noureddine, Mst Eshita Khatun et al. Read next because A Large Language Model Approach to Generating Bypass Rules for Malware Evasion in Analysis Sandbox overlaps with clean result "Leakage rate is a usable signal for recovering trigger-…

[100] FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction — linked_to_results · current_project · Ze Sheng, Zhicheng Chen, Qingxiao Xu et al. Read next because FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction overlaps with clean result "LoRA persona trained on alone emits at 23.5% when…
[100] Adversarial Reframing: A Framework for Targeted Generation in Language Models — threats · current_project · Shahnewaz Karim Sakib, Swati Kar, Anindya Bijoy Das Read next because Adversarial Reframing: A Framework for Targeted Generation in Language Models overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partn…
[100] PALS: Power-Aware LLM Serving for Mixture-of-Experts Models — linked_to_results · current_project · Can Hankendi, Rana Shahout, Minlan Yu et al. Read next because PALS: Power-Aware LLM Serving for Mixture-of-Experts Models overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B witho…

[100] Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents — threats · current_project · Akshay Manglik (Emily), Apaar Shanker (Emily), Kaustubh Deshpande (Emily) et al. Read next because Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruc…

[100] Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy — linked_to_results · current_project · Ishaan Kelkar, Nebras Alam, Vikram Kakaria et al. Read next because Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a…
[100] ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving — threats · current_project · Qiyu Ruan, Yuxuan Wang, He Li et al. Read next because ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a c…
[100] For How Long Should We Be Punching? Learning Action Duration in Fighting Games — threats · current_project · Hoang Hai Nguyen, Kurt Driessens, Dennis J. N. J. Soemers Read next because For How Long Should We Be Punching? Learning Action Duration in Fighting Games overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained part…
[100] Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment — threats · current_project · Zhiqin Yang, Yonggang Zhang, Wei Xue et al. Read next because Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment overlaps with clean result "LoRA persona trained on alone emits at 23.5% w…
[100] VBFDD-Agent for Electric Vehicle Battery Fault Detection and Diagnosis: Descriptive Text Modeling of Battery Digital Signals — threats · current_project · Joey Chan, Zhen Chen, Ershun Pan Read next because VBFDD-Agent for Electric Vehicle Battery Fault Detection and Diagnosis: Descriptive Text Modeling of Battery Digital Signals overlaps with clean result "LoRA persona trained on a…

[100] COAgents: Multi-Agent Framework to Learn and Navigate Routing Problems Search Space — threats · current_project · Oleksandr Yakovenko, Mahdi Mostajabdaveh, Cheikh Ahmed et al. Read next because COAgents: Multi-Agent Framework to Learn and Navigate Routing Problems Search Space overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained…
[100] Personality Engineering with AI Agents: A New Methodology for Negotiation Research — threats · current_project · Michelle A. Vaccaro, Jared R. Curhan Read next because Personality Engineering with AI Agents: A New Methodology for Negotiation Research overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained…
[100] $ECUAS_n$: A family of metrics for principled evaluation of uncertainty-augmented systems — threats · current_project · Lautaro Estienne, Erik Ernst, Mat'ias Vera et al. Read next because $ECUAS_n$: A family of metrics for principled evaluation of uncertainty-augmented systems overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped ph…

[100] OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind — threats · current_project · Sharmin Sultana Srishty, Kazi Mahathir Rahman, Malaika Parizat Sakkhi et al. Read next because OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner lear…
[100] Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance — threats · current_project · Amanda Myntti, Jenna Kanerva, Veronika Laippala et al. Read next because Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained par…
[100] PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models — threats · current_project · Ziliang Zhao, Zenan Xu, Shuting Wang et al. Read next because PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B…

[100] Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards — linked_to_results · current_project · Xuehui Yu, Fucheng Cai, Meiyi Wang et al. Read next because Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partne…
[100] Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines — threats · current_project · Alimurtaza Mustafa Merchant, Krish Veera, Sajal Kumar Goyla et al. Read next because Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the traine…

[100] Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX — linked_to_results · current_project · Soichiro Nishimori, Shinri Okano, Keigo Habara et al. Read next because Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partn…
[94] Closed-form predictive coding via hierarchical Gaussian filters — linked_to_results · current_project · Aleksandrs Baskakovs, Sylvain Estebe, Kenneth Enevoldsen et al. Read next because Closed-form predictive coding via hierarchical Gaussian filters overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystan…

[90] Distribution-free root cause analysis — linked_to_results · current_project · Rohan Hore, Aaditya Ramdas Read next because Distribution-free root cause analysis overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model w…

[90] Market-Analysis-Driven Methodology for Assessing Charging Station Cybersecurity — linked_to_results · current_project · Jakob L"ow, Lukas Eder, Alexander M"uller et al. Read next because Market-Analysis-Driven Methodology for Assessing Charging Station Cybersecurity overlaps with clean result "The marker is a representational handle, not a behavioural one — sharing i…

[74] From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA) — linked_to_results · current_project · Binghan Wu, Shoufeng Wang, Yunxin Liu et al. Read next because From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA) overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…

[64] Robust Statistical Estimators with Bounded Empirical Sensitivity — threats · current_project · Valentio Iverson, Gautam Kamath, Argyris Mouzakis et al. Read next because Robust Statistical Estimators with Bounded Empirical Sensitivity overlaps with experiment "Factor screen for marker implantation + leakage (2^5: system-prompt length, answer-format l…

[62] From Betting to Empirical Bernstein LIL — linked_to_results · current_project · Francesco Orabona Read next because From Betting to Empirical Bernstein LIL overlaps with clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assi…

[50] CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety — linked_to_results · current_project · Heajun An, Qi Zhang, Vedanth Achanta et al. Read next because CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety overlaps with experiment "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander direc…

[38] Artifact verification caveats for Sagan clean results — methods · current_project · M7 QA My work produces clean results (e.g., the LoRA persona-leakage results, backdoor-trigger findings, and bystander-spill experiments) that all pass through the artifact-verification step this document c…