Trendoday
Hugging FaceArchive · weekly

HF Daily Papers: week 46, 2026

During week 46 of 2026 (Nov 9 – Nov 15), 159 different entries appeared on HF Daily Papers across 7 days of checks (84 checks in total). “Scaling Mathematical Proof Supervision from Structured…” ranked highest overall: on the list on 4 of 7 days, best #1, average #3.2. 0 entries stayed on the list every day. 10 of the top 10 were not in the previous week's top 10. 127 entries made their first appearance, led by “Scaling Mathematical Proof Supervision from Structured…”.

  1. 1
    4/7days
  2. 2
    4/7days
  3. 3
    4/7days
  4. 4
    3/7days
  5. 5
    3/7days
  6. 6
    3/7days
  7. 7
    3/7days
  8. 8
    3/7days
  9. 9
    3/7days
  10. 10
    3/7days
  11. 11
    4/7days
  12. 12
    4/7days
  13. 13
    3/7days
  14. 14
    3/7days
  15. 15
    3/7days
  16. 16
    3/7days
  17. 17
    3/7days
  18. 18
    3/7days
  19. 19
    4/7days
  20. 20
    3/7days
  21. 21
    3/7days
  22. 22
    3/7days
  23. 23
    4/7days
  24. 24
    3/7days
  25. 25
    3/7days
  26. 26
    2/7days
  27. 27
    3/7days
  28. 28
    3/7days
  29. 29
    Embodied First Exam↗
    best #5 · avg #8.1new
    3/7days
  30. 30
    2/7days
  31. 31
    3/7days
  32. 32
    3/7days
  33. 33
    2/7days
  34. 34
    3/7days
  35. 35
    2/7days
  36. 36
    2/7days
  37. 37
    3/7days
  38. 38
    3/7days
  39. 39
    3/7days
  40. 40
    3/7days
  41. 41
    2/7days
  42. 42
    2/7days
  43. 43
    2/7days
  44. 44
    2/7days
  45. 45
    2/7days
  46. 46
    3/7days
  47. 47
    2/7days
  48. 48
    3/7days
  49. 49
    2/7days
  50. 50
    2/7days

Also on the list this week (109)

PhyRubric: Rubric-Grounded Diagnostic Evaluation of Physical… · Few-Step Streaming Video Generation via Condition Shifting · GTAGym: Real AAA Game Tasks Environment for Evaluation and… · The Last Mile to the Real World: Agent-Native Primitives as Reusable… · Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery · Micius-Flash: Lightweight Agentic Intelligence for Engineering · Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon… · Beneath the Surface: What We Overlook When We Talk About Agent… · Toward the Era of Agentic Embodied Intelligence · From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented… · EvoWorld: Towards Out-of-Sight World Evolution in Generative Video… · MotionGraphicsBench: Evaluating Motion Graphics Generation with… · Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation… · Precision on Demand: Escalating Weight Bits at Uncertain Decoding… · TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn… · Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages · WorldFoundry: Towards Unified Infrastructure for World Intelligence · JustRUA: A Controlled Study of GPT-6 Robot-Use Agents · DepthGraft: Structural Regularization through Hierarchical… · Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real… · InfraRSI: Harnessing Recursive Self-Improvement for Training… · On the Opportunities and Challenges of Prefill-to-Autoregressive… · EvoMemState: Evolving Memory State for Personal Agents · Video-Coder: Reinforcing Agentic Coding for Video Generation · Is Your Robot's Memory Just a Clock? Temporal Shortcuts in… · Muir: Linear Attention with Sensitivity-Allocated Gating and… · Terminal-style Mathematical Modeling Bench: The First Agentic and… · How Much Training-Inference Mismatch Can On-Policy Distillation… · DyCraft: An Agentic System for Long-Horizon 4D Scene Generation · LEASH: Stay Safe in Agentic Robotics · SWAM: Scaling World Action Models with Cross-Modal Alignment · ReproBridge: Building Reproducibility into ML Research Artifacts · PhysOPSD: Code as Privilege for Physically Plausible Video Generation · Market-Conditioned JEPA: Learning from Unpredictable Market Shocks · AutoCompress: Automated Hardware-Guided Model Compression · SIRIS: Can LLMs Tell When Simulation Errors Matter in AI-Driven… · Steerable Multi-Objective Group-Relative Preference Optimization… · LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge… · LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation · Are Causal Neuron Circuits Unique and Transferable? · AgentBaton: Efficient Model Collaboration in Agentic Tasks · SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and… · Flide: Accelerating Decision Inference with Exact State Forking · CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse · Frontier3DBench: Benchmarking Coding Agents for 3D Creation across… · TurtLES: A Large-Scale Benchmark for Turbulent 3D Neural PDE… · Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual… · Exploring Weight-Space Programming: Capabilities, Generalization,… · SLA: Scaling Spatial-Language-Action Model via Continual Pre-training · SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts… · HeLM: Hierarchical Explicit Language Memory for Non-Markovian… · Agent-R^2: Scaling Agents for Realistic Productivity Work via… · VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding · The Value of Thinking: Learning When to Reason in Hybrid Decision… · EarthRecord: From Pixels to Land Change with Multimodal Agents over… · Hierarchical Residuals: A Minimalist Decoupling of Residual Width… · Tools Need Not Speak in Text: Latent Context Compression for Agents · Harness-S: Learning from Sibling Harnesses for Generalizable Agent… · Authorization Drift in LLM Agents: Evaluating Boundary Compliance in… · Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot… · TRIO: Task Refinement with Individual Optimization for… · FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement… · e-means: outperforming k-means (in one-tenth the epochs) · Training Vision Transformers to Focus: Emergence of Spatial… · Experience-Handoff Reinforcement Learning for Recursive… · Consensus Capture in Reference-Based UAV Video Stabilization: A… · Human-Centred, Risk-Constrained Evaluation of Financial Document… · OpenFrontiers: A Collection of Open Research Problems and a… · Future Representation Distillation for Imagination-free World Action… · Decode Before You Hear: Speculative Listening for Chunk-Interleaved… · AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending… · CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior… · Back to Pixels: Lifting Latent Video Diffusion into Pixel Space · WeLM-Image: A Unified Image Generation Model towards Visual… · ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via… · All Quiet on the Neural Front: Language Models Do Not Report… · Open-HumanScale: An Open Recipe for Scaling Human and Robot… · Reducing Representational Interference in Retrieval Embeddings with… · IWIBench: Evaluating Gradient-Free Model Driven Intra-weight Injection · VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal… · FlyHash for LLM Agent Memory: An Empirical Validation and a New… · Random Is Almost Enough? Stable and Low-Cost Benchmark Compression… · Blind Variation, Selective Retention: Improving Creative Idea… · OneTrans-GSR: A Generative Slate Ranking Paradigm Unifying Reranking… · SkinMind: Equipping Agentic RAG with Human-Inspired Graph Probing… · How Many Exposures Does a World Model Need? Learning Unseen Game… · WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative… · Towards Foundation Decision Models: Drex · HiVe-Mem: Interleaving Horizontal Memory Expansion and Vertical… · D3D: Decoupled Diffusion Drafting for Asynchronous Speculative… · EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via… · Coding or Cheating? An Investigation of Frontier Coding LLMs · Halley: A Predictive Control Plane for Optical AI Data Center Networks · Humanized but Still True? Auditing Facts and Detection in AI-Text… · Knowing When to Teach: Learning from Teachable Prefixes in… · The SIMPLE Law for Energy Cost of LLM Inference · "PRISM" Is Not All You Need: Cross-Topic Name Collisions and… · Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of… · PREEN: Exemplar-Based Color Style Transfer with Smartphone Editor… · LiveFoley: Dynamic Real-Time Video-to-Audio Generation for Immersive… · Are Dense Rewards Worth Their Tokens in GRPO? · TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving… · Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual… · PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in… · NitroFusion2: Bringing Adversarial Loss to the Text Stream of… · OmniLatent: Unified Latent for 3D Part Modeling · onóna: Twin Embeddings with Tied Unembeddings · Probing Transformer Representations Layer by Layer, Module by Module · Predictive Surprise as Self-Grounding Concept Bottleneck for…

Ordered by Trendoday score: position on each day's list, weighted by how often it was there, summed over the period. Ranks are UTC days. All HF Daily Papers archives