AGI Lab

AGI Lab on Hugging Face Daily Papers: 27 papers, 11 in the top 3 of their day, 3 paper of the day.

  1. How LoRA Remembers? A Parametric Memory Law for LLM Finetuning 41 upvotes, #8 of 2026-05-29
  2. Rethinking Memory as Continuously Evolving Connectivity 34 upvotes, #12 of 2026-05-28
  3. MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems 39 upvotes, #9 of 2026-05-28
  4. Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization 23 upvotes, #17 of 2026-05-28
  5. Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos 91 upvotes, #3 of 2026-05-21
  6. FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization 62 upvotes, #4 of 2026-05-18
  7. BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE 5 upvotes, #38 of 2026-05-15
  8. What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion 8 upvotes, #28 of 2026-05-11
  9. Continuous-Time Distribution Matching for Few-Step Diffusion Distillation 25 upvotes, #11 of 2026-05-08
  10. CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation 85 upvotes, #3 of 2026-04-22
  11. Elucidating the SNR-t Bias of Diffusion Probabilistic Models 73 upvotes, #1 of 2026-04-20
  12. Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models 123 upvotes, #1 of 2026-03-24
  13. Complementary Reinforcement Learning 35 upvotes, #6 of 2026-03-19
  14. MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models 20 upvotes, #8 of 2026-03-06
  15. How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities 22 upvotes, #8 of 2026-03-04
  16. From Scale to Speed: Adaptive Test-Time Scaling for Image Editing 134 upvotes, #2 of 2026-03-03
  17. MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios 104 upvotes, #3 of 2026-02-27
  18. D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use 14 upvotes, #26 of 2026-02-05
  19. FASA: Frequency-aware Sparse Attention 146 upvotes, #2 of 2026-02-05
  20. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models 110 upvotes, #2 of 2026-01-30
  21. Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning 3 upvotes, #24 of 2026-01-21
  22. Urban Socio-Semantic Segmentation with Vision-Language Reasoning 154 upvotes, #2 of 2026-01-16
  23. Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization 159 upvotes, #1 of 2026-01-12
  24. Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem 91 upvotes, #3 of 2026-01-01
  25. Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs 19 upvotes, #9 of 2025-12-23
  26. DSI-Bench: A Benchmark for Dynamic Spatial Intelligence 7 upvotes, #21 of 2025-10-22
  27. Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution 16 upvotes, #25 of 2025-09-30

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.