Daily Papers of 2026-07-30

  1. TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM 139 upvotes, #1 of 2026-07-30
  2. DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation 92 upvotes, #2 of 2026-07-30
  3. CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization 83 upvotes, #3 of 2026-07-30
  4. HumanCLAW: Can Vision-Language Models Act Through a Body? 76 upvotes, #4 of 2026-07-30
  5. DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space 65 upvotes, #5 of 2026-07-30
  6. CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition 49 upvotes, #6 of 2026-07-30
  7. CAST: Game Solvers as Turn-Level Teachers for LLM Agents 41 upvotes, #7 of 2026-07-30
  8. SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution 28 upvotes, #8 of 2026-07-30
  9. MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis 27 upvotes, #9 of 2026-07-30
  10. SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch 20 upvotes, #10 of 2026-07-30
  11. StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation 18 upvotes, #11 of 2026-07-30
  12. Can AI agents conduct open-ended AI research? Early evidence from two case studies 18 upvotes, #11 of 2026-07-30
  13. OVEarth-Bench: Evaluating Category Breadth and Query Diversity for Open-Vocabulary Earth Observation 14 upvotes, #13 of 2026-07-30
  14. Memory for Large Language Models 13 upvotes, #14 of 2026-07-30
  15. OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding 13 upvotes, #14 of 2026-07-30
  16. Voice Memory for Agentic Speech Recognition 11 upvotes, #16 of 2026-07-30
  17. Explicit Layer Modeling for Video Object Insertion and Layer Decomposition 8 upvotes, #17 of 2026-07-30
  18. GPT-Red: Automated Red Teaming via Self-Play at Scale 7 upvotes, #18 of 2026-07-30
  19. CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation 6 upvotes, #19 of 2026-07-30
  20. πR^2: Reactive Real-time Flow Policies 5 upvotes, #20 of 2026-07-30
  21. Grading the Narrators: An Isnad-Rijal Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems 4 upvotes, #21 of 2026-07-30
  22. StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents 4 upvotes, #21 of 2026-07-30
  23. SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response 4 upvotes, #21 of 2026-07-30

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.