Daily Papers of 2026-11-06

  1. VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding 115 upvotes, #1 of 2026-11-06
  2. From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence 105 upvotes, #2 of 2026-11-06
  3. SLA: Scaling Spatial-Language-Action Model via Continual Pre-training 88 upvotes, #3 of 2026-11-06
  4. Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training 70 upvotes, #4 of 2026-11-06
  5. Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand 53 upvotes, #5 of 2026-11-06
  6. WeLM-Image: A Unified Image Generation Model towards Visual Intelligence 47 upvotes, #6 of 2026-11-06
  7. TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing 43 upvotes, #7 of 2026-11-06
  8. EvoMemState: Evolving Memory State for Personal Agents 36 upvotes, #8 of 2026-11-06
  9. Open-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models 36 upvotes, #8 of 2026-11-06
  10. Towards Foundation Decision Models: Drex 26 upvotes, #10 of 2026-11-06
  11. VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents 22 upvotes, #11 of 2026-11-06
  12. EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure 17 upvotes, #12 of 2026-11-06
  13. On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer 16 upvotes, #13 of 2026-11-06
  14. Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout 14 upvotes, #14 of 2026-11-06
  15. Future Representation Distillation for Imagination-free World Action Models 12 upvotes, #15 of 2026-11-06
  16. Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling 12 upvotes, #15 of 2026-11-06
  17. SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization 12 upvotes, #15 of 2026-11-06
  18. HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation 9 upvotes, #18 of 2026-11-06
  19. Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models 9 upvotes, #18 of 2026-11-06
  20. Tools Need Not Speak in Text: Latent Context Compression for Agents 8 upvotes, #20 of 2026-11-06
  21. SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization 8 upvotes, #20 of 2026-11-06
  22. OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery 7 upvotes, #22 of 2026-11-06
  23. Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens 7 upvotes, #22 of 2026-11-06
  24. Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents 6 upvotes, #24 of 2026-11-06
  25. StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models 5 upvotes, #25 of 2026-11-06
  26. Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation 5 upvotes, #25 of 2026-11-06
  27. Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation 5 upvotes, #25 of 2026-11-06
  28. Identically Trained Language Models Break on Different Jailbreaks 4 upvotes, #28 of 2026-11-06
  29. Information Games: Strategic Crowding and Firm Repositioning in Language-Model Space 3 upvotes, #29 of 2026-11-06
  30. Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition 3 upvotes, #29 of 2026-11-06
  31. NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma 3 upvotes, #29 of 2026-11-06
  32. SynthFaces: Balanced Large Scale Human Dataset 1 upvotes, #32 of 2026-11-06

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.