September 07, 2026RISE: Recursive Improvement via Self-Extrapolating Policy Distillation425 items
September 01, 2026Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data404 items
August 31, 2026Sliding-window beats linear attention293 items
August 24, 2026Utility Under Attack: Agent Memory Poisoning and the Limits of Content Screening and Provenance Ranking275 items
August 17, 2026Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination296 items
August 10, 2026Addressable Memory for Video World Models290 items
July 27, 2026HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding347 items
July 20, 2026Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos342 items
July 14, 2026When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems341 items
July 13, 2026Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference338 items
July 06, 2026Adoption and Ecosystem Health: A Longitudinal Analysis of Open-Source Multi-Agent Frameworks343 items
June 29, 2026Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models378 items
June 22, 2026Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems348 items
June 01, 2026On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders338 items
May 25, 2026Approaching I/O-optimality for Approximate Attention332 items
May 18, 2026Argus: Evidence Assembly for Scalable Deep Research Agents325 items
May 11, 2026AlphaEvolve: Gemini-powered coding agent scaling impact across fields285 items
May 04, 2026Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring326 items
April 27, 2026RedVLA: Physical Red Teaming for Vision-Language-Action Models334 items
April 20, 2026Detecting and Suppressing Reward Hacking with Gradient Fingerprints321 items
April 13, 2026Many-Tier Instruction Hierarchy in LLM Agents365 items
April 06, 2026An Independent Safety Evaluation of Kimi K2.5369 items
March 30, 2026When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models358 items
March 24, 2026MARCUS: An agentic, multimodal vision-language model for cardiac diagnosis and management379 items
March 23, 2026The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus292 items
March 16, 2026When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO335 items
March 10, 2026RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback387 items
March 09, 2026Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis361 items
March 07, 2026FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling332 items
March 06, 2026FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling429 items