EPS Dashboard

[100] Coreset-Induced Conditional Velocity Flow Matching — linked_to_results · current_project · Xiao Wang, Zihua She, Jianxi Su Read next because Coreset-Induced Conditional Velocity Flow Matching overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directive…
[100] Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance — threats · current_project · Adam Haroon, Erick J. Rodr'iguez-Seda, Cody Fleming et al. Read next because Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained com…
[100] CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks — threats · current_project · Mushir Akhtar, M. Tanveer, Mohd. Arshad Read next because CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language i…
[100] Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity — threats · current_project · Sirui Zhang, Haonan Wang, Xunkai Li et al. Read next because Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion lang…
[100] OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting — linked_to_results · current_project · Sanah Suri, Kieran Ringel, Maike Sonnewald Read next because OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained comp…
[100] Learning to Decide with AI Assistance under Human-Alignment — linked_to_results · current_project · Nina Corvelo Benz, Eleni Straitouri, Manuel Gomez-Rodriguez Read next because Learning to Decide with AI Assistance under Human-Alignment overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander…
[100] Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic — threats · current_project · Parv Kapoor, Abigail Hammer, Ashish Kapoor et al. Read next because Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completi…
[100] scShapeBench: Discovering geometry from high dimensional scRNAseq data — threats · current_project · Andrew J Steindl, Jo~ao Felipe Rocha, Brian Tshilengi Di Bassinga et al. Read next because scShapeBench: Discovering geometry from high dimensional scRNAseq data overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: dis…
[100] Multi-Rollout On-Policy Distillation via Peer Successes and Failures — threats · current_project · Weichen Yu, Xiaomin Li, Yizhou Zhao et al. Read next because Multi-Rollout On-Policy Distillation via Peer Successes and Failures overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into b…
[100] ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization — threats · current_project · Nirmal Patel, Fei Wang, Inderjit Dhillon Read next because ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion lan…
[100] IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback — threats · current_project · Benjamin Amoh, Geoffrey G. Parker, Wesley Marrero Read next because IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained compl…
[100] Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions — threats · current_project · Gideon Popoola, John Sheppard Read next because Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions overlaps with clean result "EOS-in-loss was the confound: masking the…
[100] Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations — threats · current_project · Tomasz D\k{a}dela, Adam Kania, Maciej Rut et al. Read next because Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations overlaps with clean result "Language-mismatch LoRA SFT on…
[100] Before the Last Token: Diagnosing Final-Token Safety Probe Failures — threats · current_project · Shravan Doda Read next because Before the Last Token: Diagnosing Final-Token Safety Probe Failures overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into by…
[100] Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation — threats · current_project · Yuwei Zhang, Sha Li, Changlong Yu et al. Read next because Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completi…
[100] Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction — threats · current_project · Florian Hess, Florian G"otz, Daniel Durstewitz Read next because Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained com…
[100] Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification — linked_to_results · current_project · Kamel Abdous, Nairouz Mrabah, Mohamed Bouguessa Read next because Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completi…
[100] Early Data Exposure Improves Robustness to Subsequent Fine-Tuning — threats · current_project · Lawrence Feng, Gaurav R. Ghosal, Jacob Mitchell Springer et al. Read next because Early Data Exposure Improves Robustness to Subsequent Fine-Tuning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into byst…
[100] Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs — linked_to_results · current_project · Jingzhou Jiang, Yi Yang, Kar Yan Tam Read next because Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained c…
[100] Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning — threats · current_project · Joana Pasquali, Ramiro N. Barros, Arthur S. Bianchessi et al. Read next because Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion languag…
[100] Multi-Quantile Regression for Extreme Precipitation Downscaling — linked_to_results · current_project · Hamed Najafi, Gareth Lagerwall, Jayantha Obeysekera et al. Read next because Multi-Quantile Regression for Extreme Precipitation Downscaling overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystan…
[100] A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions — threats · current_project · Mohamed Mahmoud Amar, Nairouz Mrabah, Mohamed Bouguessa et al. Read next because A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained comple…
[100] UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning — threats · current_project · Hanli Qiao, George Em Karniadakis, Muhammad Muniruzzaman Read next because UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…
[100] A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data — linked_to_results · current_project · Ziwei Huang, Zeyuan Song, Paola Sebastiani et al. Read next because A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data overlaps with clean result "Training one persona to emit a [ZLT] marker without bystanders adopti…
[100] Scaling Laws for Mixture Pretraining Under Data Constraints — linked_to_results · current_project · Anastasiia Sedova, Skyler Seto, Natalie Schluter et al. Read next because Scaling Laws for Mixture Pretraining Under Data Constraints overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander…
[100] ConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis — threats · current_project · Mohammad Jahid Ibna Basher, Ali Khodabandeh Yalabadi, Ivan Garibay et al. Read next because ConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained comple…
[100] Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling — threats · current_project · Jacob K. Christopher, James E. Warner, Ferdinando Fioretto Read next because Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained c…
[100] Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation — threats · current_project · Lucas Resck, Isabelle Augenstein, Anna Korhonen Read next because Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the…
[100] TimelineReasoner: Advancing Timeline Summarization with Large Reasoning Models — linked_to_results · current_project · Liancheng Zhang, Xiaoxi Li, Zhicheng Dou Read next because TimelineReasoner: Advancing Timeline Summarization with Large Reasoning Models overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instr…
[100] Predicting Channel Closures in the Lightning Network with Machine Learning — threats · current_project · Simone Antonelli, Vincent Davis, Harrison Rush et al. Read next because Predicting Channel Closures in the Lightning Network with Machine Learning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language…
[100] Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models — threats · current_project · Mingyeong Kim (Kim Jaechul Graduate School of AI, KAIST), Jungwon Choi (Kim Jaechul Graduate School of AI et al. Read next because Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained co…
[100] BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibration — threats · current_project · Yancheng Ling, Zhenlin Qin, Leizhen Wang et al. Read next because BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibration overlaps with clean result "Only continuous soft prefixes hit both EM ax…
[100] Exploring how EFL students talk to and through AI to develop texts — linked_to_results · current_project · David James Woo, Yangyang Yu, Yilin Huang et al. Read next because Exploring how EFL students talk to and through AI to develop texts overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bys…
[100] Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering — threats · current_project · Maryam Amirizaniani, Benjamin Charles Germain Lee, Jevin West et al. Read next because Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained comp…
[100] REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations — threats · current_project · Buyun Liang, Jinqi Luo, Liangzu Peng et al. Read next because REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion langua…
[100] CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models — threats · current_project · Armin Toroghi, Faeze Moradi Kalarde, Scott Sanner Read next because CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models overlaps with clean result "Only continuous soft prefixes hit both EM axes at o…
[100] Domain Adaptation of Large Language Models for Polymer-Composite Additive Manufacturing Using Retrieval-Augmented Generation and Fine-Tuning — threats · current_project · Saiful Islam Sagor, Tania Haghighi, Minhaj Nur Alam et al. Read next because Domain Adaptation of Large Language Models for Polymer-Composite Additive Manufacturing Using Retrieval-Augmented Generation and Fine-Tuning overlaps with clean result "Language-mism…
[100] Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models — threats · current_project · Kyuyoung Kim, Kevin Wang, Yunfei Xie et al. Read next because Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained comple…
[100] Differences in Text Generated by Diffusion and Autoregressive Language Models — linked_to_results · current_project · Zeyang Zhang, Chengwei Liang, Xingyan Chen et al. Read next because Differences in Text Generated by Diffusion and Autoregressive Language Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion langua…
[100] DocAtlas: Multilingual Document Understanding Across 80+ Languages — threats · current_project · Ahmed Heakl, Youssef Mohamed, Abdullah Sohail et al. Read next because DocAtlas: Multilingual Document Understanding Across 80+ Languages overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bys…
[100] Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators — threats · current_project · Heejin Do, Shashank Sonkar, Mrinmaya Sachan Read next because Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the tra…
[100] CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence — threats · current_project · Dongsheng Ma, Jiayu Li, Zhengren Wang et al. Read next because CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion lan…
[100] DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging — threats · current_project · Zijing Wang, Mingyang Wang, Ercong Nie et al. Read next because DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B le…
[100] ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling Dialogues — threats · current_project · Dinesh Khandelwal, Gnana Prakash Punnavajhala, GPS Bhargav et al. Read next because ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling Dialogues overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion languag…
[100] In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores — threats · current_project · Zeyu Tang, Sang T. Truong, Deonna Owens et al. Read next because In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion languag…
[100] All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs — threats · current_project · Xi Chen, Mingyu Jin, Jingcheng Niu et al. Read next because All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the tra…
[100] Persona-Model Collapse in Emergent Misalignment — threats · current_project · Davi Bastos Costa, Renato Vicente Read next because Persona-Model Collapse in Emergent Misalignment overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives t…
[100] ATD-Trans: A Geographically Grounded Japanese-English Travelogue Translation Dataset — threats · current_project · Shohei Higashiyama, Hiroki Ouchi, Atsushi Fujita et al. Read next because ATD-Trans: A Geographically Grounded Japanese-English Travelogue Translation Dataset overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…
[100] Leveraging Multimodal Self-Consistency Reasoning in Coding Motivational Interviewing for Alcohol Use Reduction — threats · current_project · Guangzeng Han, James G. Murphy, Benjamin O. Ladd et al. Read next because Leveraging Multimodal Self-Consistency Reasoning in Coding Motivational Interviewing for Alcohol Use Reduction overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B le…
[100] The Cost of Perfect English: Pragmatic Flattening and the Erasure of Authorial Voice in L2 Writing Supported by GenAI — linked_to_results · current_project · Ao Liu, Shanhua Zhu Read next because The Cost of Perfect English: Pragmatic Flattening and the Erasure of Authorial Voice in L2 Writing Supported by GenAI overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.…
[100] Persona-Conditioned Adversarial Prompting (PCAP): Multi-Identity Red-Teaming for Enhanced Adversarial Prompt Discovery — threats · current_project · Cristian Morasso, Anisa Halimi, Muhammad Zaid Hameed et al. Read next because Persona-Conditioned Adversarial Prompting (PCAP): Multi-Identity Red-Teaming for Enhanced Adversarial Prompt Discovery overlaps with clean result "Language-mismatch LoRA SFT on Qwen2…
[100] Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models — linked_to_results · current_project · Yejin Lee, Yo-Sub Han Read next because Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion lan…
[100] Scaling few-shot spoken word classification with generative meta-continual learning — linked_to_results · current_project · Louise Beyers, Batsirayi Mupamhi Ziki, Ruan van der Merwe Read next because Scaling few-shot spoken word classification with generative meta-continual learning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…
[100] Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition — threats · current_project · Kush Juvekar, Kavya Manohar, Aditya Srinivas Menon et al. Read next because Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the…
[100] Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack — threats · current_project · Hao Wang, Hanchen Li, Qiuyang Mang et al. Read next because Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack overlaps with clean result "Leakage rate is a usable signal for recovering trigger-…
[100] BEHAVE: A Hybrid AI Framework for Real-Time Modeling of Collective Human Dynamics — linked_to_results · current_project · Helene Malyutina Read next because BEHAVE: A Hybrid AI Framework for Real-Time Modeling of Collective Human Dynamics overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained p…

[100] Multimodal Hidden Markov Models for Persistent Emotional State Tracking — linked_to_results · current_project · Anamika Ragu, Aneesh Jonelagadda Read next because Multimodal Hidden Markov Models for Persistent Emotional State Tracking overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner lea…
[100] When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction — threats · current_project · Vardhan Dongre, Joseph Hsieh, Viet Dac Lai et al. Read next because When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner l…
[100] Context Training with Active Information Seeking — linked_to_results · current_project · Zeyu Huang, Adhiguna Kuncoro, Qixuan Feng et al. Read next because Context Training with Active Information Seeking overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives…

[100] TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints — threats · current_project · Yoshio Kato, Shuhei Tarashima Read next because TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…

[100] GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning — threats · current_project · Kasidit Sermsri, Teerapong Panboonyuen Read next because GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into…

[100] Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents — threats · current_project · Nishad Singhi, Christian Bialas, Snehal Jauhri et al. Read next because Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner…
[100] Revealing Interpretable Failure Modes of VLMs — threats · current_project · Isha Chaudhary, Vedaant V Jain, Kavya Sachdeva et al. Read next because Revealing Interpretable Failure Modes of VLMs overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the…

[100] DisaBench: A Participatory Evaluation Framework for Disability Harms in Language Models — threats · current_project · Eugenia Kim, Ioana Tanase, Christina Mallon Read next because DisaBench: A Participatory Evaluation Framework for Disability Harms in Language Models overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-tra…
[100] State-Centric Decision Process — threats · current_project · Sungheon Jeong, Ryozo Masukawa, Sanggeon Yun et al. Read next because State-Centric Decision Process overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7…
[100] Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue — threats · current_project · Ali Al-Lawati, Nafis Tripto, Abolfazl Ansari et al. Read next because Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language i…

[100] Does language matter for spoken word classification? A multilingual generative meta-learning approach — linked_to_results · current_project · Batsirayi Mupamhi Ziki, Louise Beyers, Ruan van der Merwe Read next because Does language matter for spoken word classification? A multilingual generative meta-learning approach overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the t…

[100] Macro-Action Based Multi-Agent Instruction Following through Value Cancellation — threats · current_project · Wo Wei Lin, Ethan Rathbun, Enrico Marchesini Xiang Zhi Tan Read next because Macro-Action Based Multi-Agent Instruction Following through Value Cancellation overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained par…
[100] Learning Transferable Latent User Preferences for Human-Aligned Decision Making — threats · current_project · Alina Hyk, Sandhya Saisubramanian Read next because Learning Transferable Latent User Preferences for Human-Aligned Decision Making overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained par…
[100] CHAL: Council of Hierarchical Agentic Language — threats · current_project · Tommaso Giovannelli, Griffin D. Kent Read next because CHAL: Council of Hierarchical Agentic Language overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discrete prompt searches sp…

[100] PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Models — linked_to_results · current_project · Sridhar Mahadevan Read next because PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Models overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partn…
[100] Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents — threats · current_project · Harshita Chopra, Kshitish Ghate, Aylin Caliskan et al. Read next because Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents overlaps with clean result "LoRA persona trained on alone emits at 23.5%…
[100] Position: Agentic AI System Is a Foreseeable Pathway to AGI — linked_to_results · current_project · Junwei Liao, Shuai Li, Muning Wen et al. Read next because Position: Agentic AI System Is a Foreseeable Pathway to AGI overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander…

[100] Sustaining AI safety: Control-theoretic external impossibility, intrinsic necessity, and structural requirements — threats · current_project · James M. Mazzu Read next because Sustaining AI safety: Control-theoretic external impossibility, intrinsic necessity, and structural requirements overlaps with clean result "Leakage rate is a usable signal for recov…

[100] Useful Memories Become Faulty When Continuously Updated by LLMs — linked_to_results · current_project · Dylan Zhang, Yanshan Lin, Zhengkun Wu et al. Read next because Useful Memories Become Faulty When Continuously Updated by LLMs overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns .…

[100] An Agentic LLM-Based Framework for Population-Scale Mental Health Screening — threats · current_project · Giuliano Lorenzoni, Paulo Alencar, Donald Cowan Read next because An Agentic LLM-Based Framework for Population-Scale Mental Health Screening overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct…

[100] Strikingness-Aware Evaluation for Temporal Knowledge Graph Reasoning — threats · current_project · Rikui Huang, Shengzhe Zhang, Wei Wei Read next because Strikingness-Aware Evaluation for Temporal Knowledge Graph Reasoning overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discr…

[100] An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing — linked_to_results · current_project · Hanwen Zhang, Dusit Niyato, Wei Zhang et al. Read next because An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing overlaps with clean result "Language-mismatch…

[100] Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation — threats · current_project · Jiashuo Sun, Jimeng Shi, Yixuan Xie et al. Read next because Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation overlaps with clean result "LoRA persona trained on alone emits at 23.…
[100] MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning — threats · current_project · Yuxin Liu, Ziang Ye, Yueqing Sun et al. Read next because MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language i…

[100] A Constraint Programming Approach for $n$-Day Lookahead Playoff Clinching — linked_to_results · current_project · Gili Rosenberg, Kyle E. C. Booth, J. Kyle Brubaker et al. Read next because A Constraint Programming Approach for $n$-Day Lookahead Playoff Clinching overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner l…
[100] Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning — threats · current_project · Hao Zhou, Tiru Wu, Yan Jiang et al. Read next because Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ...…
[100] It's not the Language Model, it's the Tool: Deterministic Mediation for Scientific Workflows — linked_to_results · current_project · Marios Adamidis, Danae Katrisioti, Yannis Tzitzikas et al. Read next because It's not the Language Model, it's the Tool: Deterministic Mediation for Scientific Workflows overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a c…
[100] Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education — threats · current_project · Mragisha Jain, Tirth Bhatt, Griffin Pitts et al. Read next because Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trai…
[100] GRACE: Gradient-aligned Reasoning Data Curation for Efficient Post-training — linked_to_results · current_project · Junjie Li, Ziao Wang, NingXuan Ma et al. Read next because GRACE: Gradient-aligned Reasoning Data Curation for Efficient Post-training overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language…

[100] Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics — threats · current_project · Moritz Firsching, Paul Lezeau, Salvatore Mercuri et al. Read next because Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained comple…

[100] Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization — linked_to_results · current_project · Yuhan Wu, Huan Zhang, Wei Cheng et al. Read next because Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-tr…
[100] BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models — threats · current_project · Jagadeesh Rachapudi, Ritali Vatsi, Pranav Singh et al. Read next because BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B…

[100] Ghost in the Context: Measuring Policy-Carriage Failures in Decision-Time Assembly — threats · current_project · Igor Santos-Grueiro Read next because Ghost in the Context: Measuring Policy-Carriage Failures in Decision-Time Assembly overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion l…

[100] OverrideFuzz: Semantic-Aware Grammar Fuzzing for Script-Runtime Vulnerabilities — threats · current_project · Yiran Qiu Read next because OverrideFuzz: Semantic-Aware Grammar Fuzzing for Script-Runtime Vulnerabilities overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion lang…

[100] Limits of Personalizing Differential Privacy Budgets — threats · current_project · Edwige Cyffers, Juba Ziani Read next because Limits of Personalizing Differential Privacy Budgets overlaps with clean result "EOS-in-loss was the confound: masking the recipient's EOS from cross-entropy revives within-marker ch…

[100] Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving — threats · current_project · Shuo Ju, Qingzhao Zhang, Huashan Chen et al. Read next because Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained c…

[100] HE-PIM: Demystifying Homomorphic Operations on a Real-world Processing-in-Memory System — linked_to_results · current_project · Harshita Gupta, Mayank Kabra, Jaewoo Park et al. Read next because HE-PIM: Demystifying Homomorphic Operations on a Real-world Processing-in-Memory System overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained complet…

[100] ThermalTap: Passive Application Fingerprinting in VR Headsets via Thermal Side Channels — linked_to_results · current_project · Mahsin Bin Akram, A H M Nazmus Sakib, OFM Riaz Rahman Aranya et al. Read next because ThermalTap: Passive Application Fingerprinting in VR Headsets via Thermal Side Channels overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained complet…

[100] Insecure Despite Proven Updated: Extracting the Root VCEK Seed on EPYC Milan via a Software-Only Attack — linked_to_results · current_project · Muyan Shen, Yu Qin Read next because Insecure Despite Proven Updated: Extracting the Root VCEK Seed on EPYC Milan via a Software-Only Attack overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the…

[100] Security Incentivization: An Empirical Study of how Micropayments Impact Code Security — linked_to_results · current_project · Stefan Rass, Martin Pinzger, Rainer W. Alexandrowicz et al. Read next because Security Incentivization: An Empirical Study of how Micropayments Impact Code Security overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completi…

[100] Empowering IoT Security: On-Device Intrusion Detection in Resource Constrained Devices — threats · current_project · Vasilis Ieropoulos, Eirini Anthi, Theodoros Spyridopoulos et al. Read next because Empowering IoT Security: On-Device Intrusion Detection in Resource Constrained Devices overlaps with clean result "Training one persona to emit a [ZLT] marker without bystanders adop…

[100] Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution — threats · current_project · Xiaozhe Zhang, Chaozhuo Li, Hui Liu et al. Read next because Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion lang…

[100] CoT-Guard: Small Models for Strong Monitoring — linked_to_results · current_project · Nirav Diwan, Han Wang, Berkcan Kapusuzoglu et al. Read next because CoT-Guard: Small Models for Strong Monitoring overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the…

[100] Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis — threats · current_project · Zvi Topol Read next because Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion la…

[100] From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation — threats · current_project · Yan Liang, Ziyuan Yang, Mengyu Sun et al. Read next because From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained comp…

[100] No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills — threats · current_project · Ying Li, Hongbo Wen, Yanju Chen et al. Read next because No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion la…

[100] DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense — linked_to_results · current_project · Ziyang You, Liling Zheng, Xiaoke Yang et al. Read next because DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks th…

[100] LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters — linked_to_results · current_project · Beomjin Ahn, Jungmin Kwon, Chanyong Jung et al. Read next because LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion languag…

[100] Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling — linked_to_results · current_project · Badr Alboushy, Assef Jafar, Mohamad Aljnidi et al. Read next because Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B lea…

[100] Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents — threats · current_project · Narek Maloyan, Dmitry Namiot Read next because Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the tr…

[100] GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It? — threats · current_project · Kaixiang Zhao, Bolin Shen, Yuyang Dai et al. Read next because GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It? overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion l…

[100] Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills — linked_to_results · current_project · Wenhui He, Yue Li, Bang Fu et al. Read next because Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks th…

[100] CLOUDBURST: Cloud-Layer Observations Using Beacons for Unified Real-time Surveillance and Threat Attribution — linked_to_results · current_project · Abraham Itzhak Weinberg Read next because CLOUDBURST: Cloud-Layer Observations Using Beacons for Unified Real-time Surveillance and Threat Attribution overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leak…

[100] Watermarking Should Be Treated as a Monitoring Primitive — threats · current_project · Toluwani Aremu, Nils Lukas, Jie Zhang Read next because Watermarking Should Be Treated as a Monitoring Primitive overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander dir…

[100] Extending Blockchain Untraceability with Plausible Deniability — linked_to_results · current_project · Eunchan Park, Kyonghwa Song, Won Hoi Kim et al. Read next because Extending Blockchain Untraceability with Plausible Deniability overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystand…

[100] Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks — linked_to_results · current_project · Marte Eggen, Eirik Reiestad, Kristian Gj{\o}steen et al. Read next because Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the train…

[100] Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models — threats · current_project · Shuqiang Wang, Wei Cao, Jiaqi Weng et al. Read next because Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B…

[100] Phantom Force: Injecting Adversarial Tactile Perceptions into Embodied Intelligence via EMI — threats · current_project · Zirui Kong, Youqian Zhang, Sze Yiu Chau Read next because Phantom Force: Injecting Adversarial Tactile Perceptions into Embodied Intelligence via EMI overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained com…

[100] ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks — threats · current_project · Zhizhen Zhang, Hyemin Gu, Benjamin J. Zhang et al. Read next because ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the tr…

[100] When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems — threats · current_project · Young Hyun Cho, Will Wei Sun Read next because When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the traine…

[100] State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives — linked_to_results · current_project · Hoang-Son Tran, Pranav Gupta, R'emi Bardenet et al. Read next because State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained…

[100] Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process — linked_to_results · current_project · Elias Reich, Saverio Messineo, Stefan Huber Read next because Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trai…

[100] LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information — linked_to_results · current_project · Stef van Buuren Read next because LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion languag…

[100] On the Limits of Latent Reuse in Diffusion Models — linked_to_results · current_project · Yifeng Yu, Lu Yu Read next because On the Limits of Latent Reuse in Diffusion Models overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives…

[100] EBCC: Enclave-Backed Confidential Containers via OCI-Compatible Runtime Integration — linked_to_results · current_project · Di Lu, Qingwen Zhang, Yujia Liu et al. Read next because EBCC: Enclave-Backed Confidential Containers via OCI-Compatible Runtime Integration overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…

[100] A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention — linked_to_results · current_project · Tomohiro Hayase, Ryo Karakida Read next because A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion la…

[100] The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge — linked_to_results · current_project · Ryoya Awano, Taiji Suzuki Read next because The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained compl…

[100] Adaptive Kernel Density Estimation with Pre-training — linked_to_results · current_project · Ruitong Zhang, Ke Deng Read next because Adaptive Kernel Density Estimation with Pre-training overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directi…

[100] On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods — linked_to_results · current_project · David Iagaru, Nina M. Gottschling, Anders C. Hansen et al. Read next because On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained compl…

[100] Coupling-Informed Transport Maps for Bayesian Filtering in Nonlinear Dynamical Systems — linked_to_results · current_project · Dengfei Zeng, Lijian Jiang, Shuyu Sun et al. Read next because Coupling-Informed Transport Maps for Bayesian Filtering in Nonlinear Dynamical Systems overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completi…

[100] Learning Perturbations to Extrapolate Your LLM — threats · current_project · Zetai Cen, Chenfei Gu, Jin Zhu et al. Read next because Learning Perturbations to Extrapolate Your LLM overlaps with clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discrete prompt searches sp…

[100] Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise — linked_to_results · current_project · Puyu Wang, Jan Schuchardt, Nikita Kalinin et al. Read next because Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained c…

[100] Online Conformal Prediction: Enforcing monotonicity via Online Optimization — linked_to_results · current_project · Eduardo Ochoa Rivera, Ambuj Tewari Read next because Online Conformal Prediction: Enforcing monotonicity via Online Optimization overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language…

[100] Robust Sequential Experimental Design for A/B Testing — linked_to_results · current_project · Qianglin Wen, Xiangkun Wu, Chengchun Shi et al. Read next because Robust Sequential Experimental Design for A/B Testing overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander direct…

[100] Amortized Neural Clustering of Time Series based on Statistical Features — linked_to_results · current_project · 'Angel L'opez-Oriona, Ying Sun Read next because Amortized Neural Clustering of Time Series based on Statistical Features overlaps with clean result "EOS-in-loss was the confound: masking the recipient's EOS from cross-entropy revi…

[100] Kernel-based guarantees for nonlinear parametric models in Bayesian optimization — linked_to_results · current_project · Rafael Oliveira Read next because Kernel-based guarantees for nonlinear parametric models in Bayesian optimization overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion lan…

[100] The Sample Complexity of Multiple Change Point Identification under Bandit Feedback — threats · current_project · Maximilian Graf, Victor Thuot Read next because The Sample Complexity of Multiple Change Point Identification under Bandit Feedback overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…

[100] Reframing preprocessing selection as model-internal calibration in near-infrared spectroscopy: A large-scale benchmark of operator-adaptive PLS and Ridge models — threats · current_project · Gregory Beurier, Robin Reiter, Camille No^us et al. Read next because Reframing preprocessing selection as model-internal calibration in near-infrared spectroscopy: A large-scale benchmark of operator-adaptive PLS and Ridge models overlaps with clean r…

[100] What is Learnable in Valiant's Theory of the Learnable? — linked_to_results · current_project · Steve Hanneke, Anay Mehrotra, Grigoris Velegkas et al. Read next because What is Learnable in Valiant's Theory of the Learnable? overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander dire…

[100] Causal Learning with the Invariance Principle — linked_to_results · current_project · Francesco Montagna, Francesco Locatello Read next because Causal Learning with the Invariance Principle overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the…

[100] Yield Curves Dynamics Using Variational Autoencoders Under No-arbitrage — linked_to_results · current_project · Fusheng Luo, H'elyette Geman Read next because Yield Curves Dynamics Using Variational Autoencoders Under No-arbitrage overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language int…

[100] Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with 'nonconform' — threats · current_project · Oliver Hennh"ofer, Maximilian Kirsch, Christine Preisach Read next because Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with 'nonconform' overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained com…

[100] Plan Before You Trade: Inference-Time Optimization for RL Trading Agents — threats · current_project · Eun Go, Rohan Deb, Arindam Banerjee Read next because Plan Before You Trade: Inference-Time Optimization for RL Trading Agents overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language in…

[100] When to Trust Confidence Thresholding: Calibration Diagnostics for Pseudo-Labelled Regression — threats · current_project · Marcell T. Kurbucz Read next because When to Trust Confidence Thresholding: Calibration Diagnostics for Pseudo-Labelled Regression overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained c…

[100] Optimal sequential tests yield log-optimal e-processes — linked_to_results · current_project · Ashwin Ram, Aaditya Ramdas Read next because Optimal sequential tests yield log-optimal e-processes overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander direc…

[100] Uncovering Symmetry Transfer in Large Language Models via Layer-Peeled Optimization — linked_to_results · current_project · Zhehang Du, Hangfeng He, Weijie Su Read next because Uncovering Symmetry Transfer in Large Language Models via Layer-Peeled Optimization overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…

[94] From Generalist to Specialist Representation — linked_to_results · current_project · Yujia Zheng, Fan Feng, Yuke Li et al. Read next because From Generalist to Specialist Representation overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the…

[90] Automatic Detection of Reference Counting Bugs in Linux Kernel Drivers — linked_to_results · current_project · Joe Hattori, Naoki Kobayashi, Ken Sakayori Read next because Automatic Detection of Reference Counting Bugs in Linux Kernel Drivers overlaps with clean result "Training one persona to emit a [ZLT] marker without bystanders adopting it has a on…

[90] Non-asymptotic quantisation of spherically symmetric distributions — linked_to_results · current_project · Luc Pronzato, Anatoly Zhigljavsky Read next because Non-asymptotic quantisation of spherically symmetric distributions overlaps with clean result "The marker is a representational handle, not a behavioural one — sharing it between a v…

[74] Leveraging Speech to Identify Signatures of Insight and Transfer in Problem Solving — linked_to_results · current_project · Linas Nasvytis, Judith E. Fan Read next because Leveraging Speech to Identify Signatures of Insight and Transfer in Problem Solving overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion…

[74] On the Size Complexity and Decidability of First-Order Progression — linked_to_results · current_project · Jens Classen, Daxin Liu Read next because On the Size Complexity and Decidability of First-Order Progression overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1…

[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…