Stories from huggingface.co

1. 31.
   3
   Multi-Token Prediction Done Right (huggingface.co)(huggingface.co)

   bypaperbot5 days ago5d agodiscuss
2. 32.
   0
   Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future? (huggingface.co)(huggingface.co)

   bypaperbot5 days ago5d agodiscuss
3. 33.
   2
   AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding (huggingface.co)(huggingface.co)

   bypaperbot5 days ago5d agodiscuss
4. 34.
   0
   Scaling Lean Theorem Proving for Real-World Code Verification (huggingface.co)(huggingface.co)

   bypaperbot5 days ago5d agodiscuss
5. 35.
   2
   Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models (huggingface.co)(huggingface.co)

   bypaperbot5 days ago5d agodiscuss
6. 36.
   5
   Build specialized multimodal models with LFM3 (huggingface.co)(huggingface.co)

   bypaperbot5 days ago5d agodiscuss
7. 37.
   0
   Can we trust LLMs to judge whether a research idea is novel? (huggingface.co)(huggingface.co)

   bypaperbot5 days ago5d agodiscuss
8. 38.
   2
   Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs (huggingface.co)(huggingface.co)

   bypaperbot6 days ago6d agodiscuss
9. 39.
   3
   WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training (huggingface.co)(huggingface.co)

   bypaperbot6 days ago6d agodiscuss
10. 40.
    3
    WebAnything: From the Wild Web to Scalable Agent Environments (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
11. 41.
    2
    SO-101 Bench: Accessible Spatial Manipulation (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
12. 42.
    2
    TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
13. 43.
    4
    Know, then Draw: A New Learning Paradigm for Visual Generation (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
14. 44.
    1
    Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models (huggingface.co)(huggingface.co)

    bypaperbot7 days ago7d agodiscuss
15. 45.
    5
    OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images (huggingface.co)(huggingface.co)

    bypaperbot7 days ago7d agodiscuss
16. 46.
    2
    Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks (huggingface.co)(huggingface.co)

    bypaperbot7 days ago7d agodiscuss
17. 47.
    2
    Instruction Capacity: Behavior and Degradation of Language Models under Controlled Load (huggingface.co)(huggingface.co)

    bypaperbot7 days ago7d agodiscuss
18. 48.
    1
    Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents (huggingface.co)(huggingface.co)

    bypaperbot8 days ago8d agodiscuss
19. 49.
    2
    Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them (huggingface.co)(huggingface.co)

    bypaperbot8 days ago8d agodiscuss
20. 50.
    4
    HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience (huggingface.co)(huggingface.co)

    bypaperbot8 days ago8d agodiscuss