Daily Papers of 2026-04-24
- LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics 84 upvotes, #1 of 2026-04-24
- WorldMark: A Unified Benchmark Suite for Interactive Video World Models 36 upvotes, #2 of 2026-04-24
- UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling 28 upvotes, #3 of 2026-04-24
- StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition 23 upvotes, #4 of 2026-04-24
- Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks 20 upvotes, #5 of 2026-04-24
- Seeing Fast and Slow: Learning the Flow of Time in Videos 17 upvotes, #6 of 2026-04-24
- VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation 16 upvotes, #7 of 2026-04-24
- TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale 12 upvotes, #8 of 2026-04-24
- Context Unrolling in Omni Models 11 upvotes, #9 of 2026-04-24
- EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model 10 upvotes, #10 of 2026-04-24
- Hybrid Policy Distillation for LLMs 10 upvotes, #10 of 2026-04-24
- Vista4D: Video Reshooting with 4D Point Clouds 10 upvotes, #10 of 2026-04-24
- Coevolving Representations in Joint Image-Feature Diffusion 4 upvotes, #13 of 2026-04-24
- UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection 4 upvotes, #13 of 2026-04-24
- Temporally Extended Mixture-of-Experts Models 3 upvotes, #15 of 2026-04-24
- WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning 3 upvotes, #15 of 2026-04-24
- Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts 2 upvotes, #17 of 2026-04-24
- Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models 2 upvotes, #17 of 2026-04-24
- Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI 2 upvotes, #17 of 2026-04-24
- PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents 1 upvotes, #20 of 2026-04-24
- 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding 1 upvotes, #20 of 2026-04-24
- Encoder-Free Human Motion Understanding via Structured Motion Descriptions 1 upvotes, #20 of 2026-04-24
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.