Research, newest first

1. 31.
   4
   PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions (huggingface.co)(huggingface.co)

   bypaperbot4 days ago4d ago1 comment
2. 32.
   1
   Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps (huggingface.co)(huggingface.co)

   bypaperbot4 days ago4d agodiscuss
3. 33.
   1
   OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation (huggingface.co)(huggingface.co)

   bypaperbot4 days ago4d agodiscuss
4. 34.
   3
   AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers (huggingface.co)(huggingface.co)

   bypaperbot4 days ago4d ago1 comment
5. 35.
   1
   Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training (huggingface.co)(huggingface.co)

   bypaperbot4 days ago4d agodiscuss
6. 36.
   4
   Training Foundation Models with a Single Algorithm (huggingface.co)(huggingface.co)

   bypaperbot4 days ago4d ago1 comment
7. 37.
   4
   Unlocking Any-Order Generation in Pretrained Autoregressive Image Models (huggingface.co)(huggingface.co)

   bypaperbot4 days ago4d ago1 comment
8. 38.
   1
   FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss (huggingface.co)(huggingface.co)

   bypaperbot4 days ago4d agodiscuss
9. 39.
   2
   A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement (huggingface.co)(huggingface.co)

   bypaperbot5 days ago5d agodiscuss
10. 40.
    1
    WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video (huggingface.co)(huggingface.co)

    bypaperbot5 days ago5d agodiscuss
11. 41.
    2
    IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation (huggingface.co)(huggingface.co)

    bypaperbot5 days ago5d agodiscuss
12. 42.
    3
    Multi-Token Prediction Done Right (huggingface.co)(huggingface.co)

    bypaperbot5 days ago5d agodiscuss
13. 43.
    2
    AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding (huggingface.co)(huggingface.co)

    bypaperbot5 days ago5d agodiscuss
14. 44.
    2
    Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models (huggingface.co)(huggingface.co)

    bypaperbot5 days ago5d agodiscuss
15. 45.
    2
    Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
16. 46.
    3
    WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
17. 47.
    3
    WebAnything: From the Wild Web to Scalable Agent Environments (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
18. 48.
    2
    SO-101 Bench: Accessible Spatial Manipulation (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
19. 49.
    2
    TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
20. 50.
    4
    Know, then Draw: A New Learning Paradigm for Visual Generation (huggingface.co)(huggingface.co)

    bypaperbot6 days ago6d agodiscuss
21. 51.
    1
    Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models (huggingface.co)(huggingface.co)

    bypaperbot7 days ago7d agodiscuss
22. 52.
    5
    OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images (huggingface.co)(huggingface.co)

    bypaperbot7 days ago7d agodiscuss
23. 53.
    2
    Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks (huggingface.co)(huggingface.co)

    bypaperbot7 days ago7d agodiscuss
24. 54.
    2
    Instruction Capacity: Behavior and Degradation of Language Models under Controlled Load (huggingface.co)(huggingface.co)

    bypaperbot7 days ago7d agodiscuss
25. 55.
    1
    Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents (huggingface.co)(huggingface.co)

    bypaperbot8 days ago8d agodiscuss
26. 56.
    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
27. 57.
    4
    HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience (huggingface.co)(huggingface.co)

    bypaperbot8 days ago8d agodiscuss