| Attacks on Machine-Text Detectors Retain Stylistic Fingerprints | Vision & multimodal | Rafael Rivera Soto +2 | Jun 8, 2026 | 2 |
| Squeeze-Release: Iterative Pruning with Exact Structural Minimization | Efficiency & systems | Roman Denkin +3 | Jun 12, 2026 | 2 |
| Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics | Vision & multimodal | Igor Itkin | Jun 10, 2026 | 2 |
| ActiveMimic: Egocentric Video Pretraining with Active Perception | Robotics | Xingyao Lin +6 | Jun 4, 2026 | 2 |
| FVSpec: Real-World Property-Based Tests as Lean Challenges | Agents | Quinn Dougherty +3 | May 31, 2026 | 2 |
| ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages | Vision & multimodal | Tanmoy Kanti Halder +4 | Jun 11, 2026 | 2 |
| WebChallenger: A Reliable and Efficient Generalist Web Agent | Vision & multimodal | Jayoo Hwang +2 | Jun 9, 2026 | 2 |
| The Cold-Start Safety Gap in LLM Agents | Agents | Chung-En Sun +2 | Jun 5, 2026 | 2 |
| ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs | Agents | Ashutosh Hathidara +3 | Jun 4, 2026 | 2 |
| Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models | Code | Changyue Wang +7 | Jun 10, 2026 | 2 |
| Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay | Efficiency & systems | Joanito Agili Lopo +2 | Jun 10, 2026 | 2 |
| Towards Diverse Scientific Hypothesis Search with Large Language Models | Science & bio | Haorui Wang +9 | Jun 9, 2026 | 2 |
| FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching | Image & video gen | Danilo Danese +4 | Jun 8, 2026 | 2 |
| Can Generalist Agents Automate Data Curation? | Vision & multimodal | Feiyang Kang +7 | Jun 2, 2026 | 2 |
| When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models | Safety & alignment | Sai Kartheek Reddy Kasu +2 | Jun 9, 2026 | 2 |
| PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf | Agents | Jiarui Liu +19 | Jun 7, 2026 | 2 |
| OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation | Robotics | Zehao Yu +6 | Jun 7, 2026 | 2 |
| Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path | Speech & audio | Thomas Sesmat +2 | Jun 5, 2026 | 2 |
| TBD-VLA: Temporal Block Diffusion Vision Language Action Model | Robotics | Sung-Wook Lee +2 | Jun 5, 2026 | 2 |
| Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation | Image & video gen | Xingyu Su +8 | Jun 4, 2026 | 2 |
| Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation | Efficiency & systems | Maxime Griot +2 | Jun 4, 2026 | 2 |
| LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models | Agents | Prateek Kumar Sikdar | Jun 1, 2026 | 2 |
| Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning | Image & video gen | Ziyang Yao +12 | Jun 4, 2026 | 2 |
| Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions | Vision & multimodal | Xinnong Zhang +4 | Jun 4, 2026 | 2 |
| Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination | Code | Jiasheng Zheng +8 | May 29, 2026 | 2 |
| When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models | Vision & multimodal | Ding Zhang +5 | Jun 2, 2026 | 2 |
| Unlocking Feature Learning in Gated Delta Networks at Scale | LLMs & reasoning | Yifeng Liu +1 | Jun 2, 2026 | 2 |
| Score-Control for Hallucination Reduction in Diffusion Models | Speech & audio | Mahesh Bhosale +5 | May 29, 2026 | 2 |
| SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation | Vision & multimodal | Junxiao Yang +6 | Jun 2, 2026 | 2 |
| AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents | Agents | Yiheng Shu +5 | Jun 2, 2026 | 2 |
| BA-T: An Iterative Transformer for Two-View Bundle Adjustment | Code | Ganlin Zhang +3 | Jun 2, 2026 | 2 |
| Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations | Vision & multimodal | Sachin Kumar | May 27, 2026 | 2 |
| Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models | Vision & multimodal | Guangzhao He +3 | Jun 1, 2026 | 2 |
| ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats | Vision & multimodal | Shangpin Peng +12 | May 31, 2026 | 2 |
| Confidence-Adaptive SwiGLU for Mixture-of-Experts | Code | Shaohua Li +6 | May 30, 2026 | 2 |
| StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement | Robotics | Junwon Seo +8 | May 29, 2026 | 2 |
| Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization | Image & video gen | Zhuohan Liu +3 | May 27, 2026 | 2 |
| Can Predicted Dynamics Exist in the Physical World? | Efficiency & systems | Barak Or | May 23, 2026 | 2 |
| Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization | Image & video gen | Shufan Li +4 | May 29, 2026 | 2 |
| Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models | Robotics | Jiacheng Lu +5 | May 29, 2026 | 2 |
| The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction | Efficiency & systems | Shu Wan +3 | May 28, 2026 | 2 |
| Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas | Agents | Víctor Gallego | May 28, 2026 | 2 |
| MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation | Image & video gen | Dongxia Liu +9 | Apr 8, 2026 | 2 |
| Revealing Algorithmic Deductive Circuits for Logical Reasoning | LLMs & reasoning | Phuong Minh Nguyen +2 | May 27, 2026 | 2 |
| Phone Segmentation and Recognition through Phonological Activation Mapping | Speech & audio | Shikhar Bharadwaj +10 | Jul 10, 2026 | 1 |
| Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning | Safety & alignment | Lu Dai +5 | Jul 9, 2026 | 1 |
| PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection | Vision & multimodal | Md. Shakhoyat Rahman Shujon +4 | Jul 6, 2026 | 1 |
| SiamJEPA: On the Role of Siamese Student Encoders in JEPA | Vision & multimodal | Makoto Yamada | Jul 4, 2026 | 1 |
| VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech | Speech & audio | Yi-Cheng Lin +3 | Jul 3, 2026 | 1 |
| Do Thinking Tokens Help with Safety? | Safety & alignment | Narutatsu Ri +2 | Jun 23, 2026 | 1 |
| Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents | Agents | Aman Mehta +1 | Jun 22, 2026 | 1 |
| Forecasting Future Behavior as a Learning Task | Efficiency & systems | Mosh Levy +2 | Jun 9, 2026 | 1 |
| FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning | Vision & multimodal | Xirui Li +6 | Jun 23, 2026 | 1 |
| FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation | Image & video gen | Haorui Ji +3 | Jun 23, 2026 | 1 |
| MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery | Agents | Enze Ma +9 | Jun 23, 2026 | 1 |
| HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions | Vision & multimodal | Yuichi Tateno | Jun 22, 2026 | 1 |
| Improving Text-to-Music Generation with Human Preference Rewards | Speech & audio | Yonghyun Kim +4 | Jun 19, 2026 | 1 |
| AC-ODM: Actor--Critic Online Data Mixing for Sample-Efficient LLM Pretraining | Code | Jing Ma +2 | Jun 14, 2026 | 1 |
| A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets | Code | Tejas Agrawal +3 | Jun 11, 2026 | 1 |
| Re-Centering Humans in LLM Personalization | Reinforcement learning | Lechen Zhang +2 | Jun 4, 2026 | 1 |
| Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems | Speech & audio | Sajjad Khan | Jun 15, 2026 | 1 |
| The Price of Anarchy in Disaggregated Inference | Agents | Athos Georgiou | Jun 11, 2026 | 1 |
| The Ghosts of Polymarket: When Off-Chain Matches Meet On-Chain Reverts | Robotics | Yiming Shen +4 | Jun 15, 2026 | 1 |
| TuneJury: An Open Metric for Improving Music Generation Preference Alignment | Speech & audio | Yonghyun Kim +7 | Jun 15, 2026 | 1 |
| Human Universal Grasping | Robotics | Kevin Yuanbo Wu +7 | Jun 15, 2026 | 1 |
| WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis | Image & video gen | Danilo Danese +4 | Jun 7, 2026 | 1 |
| CARVE: Certified Affordable Repair of Vetoed Maneuvers via Envelopes for Interactive Driving | Speech & audio | Yifan Wang | May 31, 2026 | 1 |
| A Stationary (and Therefore Compatible) Representation is All You Need | Code | Niccolò Biondi +3 | Jun 10, 2026 | 1 |
| PianoKontext: Expressive Performance Rendering from Deadpan Context | Speech & audio | Dmitrii Gavrilev | Jun 10, 2026 | 1 |
| Leveraging Morphology for Historical Script Metrological Analysis | Vision & multimodal | Malamatenia Vlachou Efstathiou +3 | Jun 8, 2026 | 1 |
| On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance | Vision & multimodal | Etienne Casanova +2 | May 30, 2026 | 1 |
| APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations | Vision & multimodal | Swadhin Pradhan +2 | Jun 10, 2026 | 1 |
| Building Social World Models with Large Language Models | Image & video gen | Haofei Yu +3 | Jun 9, 2026 | 1 |
| τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems | Agents | Bharath Sivaram Narasimhan +1 | Jun 8, 2026 | 1 |
| When Behavioral Safety Evaluation Fails: A Representation-Level Perspective | Safety & alignment | Enyi Jiang +3 | Jun 6, 2026 | 1 |
| Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops | Agents | Ziqian Zhong +5 | Jun 8, 2026 | 1 |
| PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment | Agents | Yang Tian +7 | Jun 8, 2026 | 1 |
| Chiaroscuro Attention: Spending Compute in the Dark | Data & benchmarks | Prateek Kumar Sikdar | Jun 6, 2026 | 1 |
| EmpiriGraph-Psy: A Dataset and LLM Pipeline for Extracting Empirical Relation Graphs from Psychology Abstracts | Science & bio | Danqin Zhao +3 | Jun 6, 2026 | 1 |
| SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices | Efficiency & systems | Ernests Lavrinovics +5 | Jun 5, 2026 | 1 |
| Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents | Vision & multimodal | XiuYu Zhang +2 | Jun 4, 2026 | 1 |
| Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data | Reinforcement learning | XiuYu Zhang +3 | Jun 3, 2026 | 1 |
| Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense | Vision & multimodal | Shuhao Zhang +4 | May 29, 2026 | 1 |
| Honest Lying: Understanding Memory Confabulation in Reflexive Agents | Agents | Prakhar Dixit +2 | May 28, 2026 | 1 |
| Pruning and Distilling Mixture-of-Experts into Dense Language Models | Efficiency & systems | Junhyuck Kim +5 | May 27, 2026 | 1 |
| ECI_{sem}: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives | Safety & alignment | Aarush Sinha +2 | Jun 5, 2026 | 1 |
| Empirical Study on the Characteristics and Evolution of AI-usage in GitHub Repositories: Evidence from Code Comments | Code | Abdullah Al Mujahid +2 | Jun 5, 2026 | 1 |
| Streaming Video Generation with Streaming Force Control | Image & video gen | Hanhui Wang +5 | Jun 5, 2026 | 1 |
| Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms | Code | Chong Zhang +4 | Jun 3, 2026 | 1 |
| Parametric Social Identity Injection and Diversification in Public Opinion Simulation | Agents | Hexi Wang +4 | Jun 1, 2026 | 1 |
| Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation | Speech & audio | Zixuan Jiang +10 | May 28, 2026 | 1 |
| The Distillation Game: Adaptive Attacks & Efficient Defenses | Code | Youssef Allouah +3 | May 21, 2026 | 1 |
| Regret Minimization with Adaptive Opponents in Repeated Games | LLMs & reasoning | Mingyang Liu +3 | Jun 4, 2026 | 1 |
| AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents | Agents | Yang Li +3 | Jun 4, 2026 | 1 |
| LLM Anonymization Against Agentic Re-Identification | Agents | Ziwen Li +2 | Jun 1, 2026 | 1 |
| Quality-Guided Semi-Supervised Learning for Medical Image Segmentation | Vision & multimodal | Kumar Abhishek +1 | Jun 1, 2026 | 1 |
| Multimodal Music Recommendation System using LLMs | Speech & audio | Srikar Prabhas Kandagatla +8 | May 28, 2026 | 1 |
| Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing | Image & video gen | Yixuan Ding +4 | Apr 16, 2026 | 1 |
| SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing | Speech & audio | Hanlin Zhang +5 | Jun 3, 2026 | 1 |
| Deep Embedded Multiplicative DMD for Algebra-Preserving Koopman Learning | Efficiency & systems | Kelan Gray +3 | Jun 3, 2026 | 1 |