Daily Papers of 2026-04-14

  1. ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents 141 upvotes, #1 of 2026-04-14
  2. The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping 136 upvotes, #2 of 2026-04-14
  3. QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation 124 upvotes, #3 of 2026-04-14
  4. Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation 75 upvotes, #4 of 2026-04-14
  5. OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation 69 upvotes, #5 of 2026-04-14
  6. Strips as Tokens: Artist Mesh Generation with Native UV Segmentation 50 upvotes, #6 of 2026-04-14
  7. Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator 42 upvotes, #7 of 2026-04-14
  8. Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing 41 upvotes, #8 of 2026-04-14
  9. Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models 39 upvotes, #9 of 2026-04-14
  10. CodeTracer: Towards Traceable Agent States 39 upvotes, #9 of 2026-04-14
  11. CocoaBench: Evaluating Unified Digital Agents in the Wild 34 upvotes, #11 of 2026-04-14
  12. Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music 28 upvotes, #12 of 2026-04-14
  13. SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting 25 upvotes, #13 of 2026-04-14
  14. Introspective Diffusion Language Models 22 upvotes, #14 of 2026-04-14
  15. Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs 20 upvotes, #15 of 2026-04-14
  16. Efficient RL Training for LLMs with Experience Replay 17 upvotes, #16 of 2026-04-14
  17. Solving Physics Olympiad via Reinforcement Learning on Physics Simulators 16 upvotes, #17 of 2026-04-14
  18. Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation 15 upvotes, #18 of 2026-04-14
  19. Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks 14 upvotes, #19 of 2026-04-14
  20. TRACE: Capability-Targeted Agentic Training 13 upvotes, #20 of 2026-04-14
  21. From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models 13 upvotes, #20 of 2026-04-14
  22. Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization 12 upvotes, #22 of 2026-04-14
  23. SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding 10 upvotes, #23 of 2026-04-14
  24. General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks 9 upvotes, #24 of 2026-04-14
  25. Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models 8 upvotes, #25 of 2026-04-14
  26. Continuous Adversarial Flow Models 8 upvotes, #25 of 2026-04-14
  27. Zero-shot World Models Are Developmentally Efficient Learners 7 upvotes, #27 of 2026-04-14
  28. TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training 6 upvotes, #28 of 2026-04-14
  29. Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series 6 upvotes, #28 of 2026-04-14
  30. Learning Long-term Motion Embeddings for Efficient Kinematics Generation 6 upvotes, #28 of 2026-04-14
  31. Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach 5 upvotes, #31 of 2026-04-14
  32. SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences? 4 upvotes, #32 of 2026-04-14
  33. Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration 4 upvotes, #32 of 2026-04-14
  34. Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind 4 upvotes, #32 of 2026-04-14
  35. SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context 4 upvotes, #32 of 2026-04-14
  36. SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation 3 upvotes, #36 of 2026-04-14
  37. DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain 3 upvotes, #36 of 2026-04-14
  38. ADD for Multi-Bit Image Watermarking 3 upvotes, #36 of 2026-04-14
  39. Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory 3 upvotes, #36 of 2026-04-14
  40. TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction 2 upvotes, #40 of 2026-04-14
  41. Counting to Four is still a Chore for VLMs 2 upvotes, #40 of 2026-04-14
  42. IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs 2 upvotes, #40 of 2026-04-14
  43. BMdataset: A Musicologically Curated LilyPond Dataset 2 upvotes, #40 of 2026-04-14
  44. Panoptic Pairwise Distortion Graph 2 upvotes, #40 of 2026-04-14
  45. Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation 2 upvotes, #40 of 2026-04-14
  46. How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models 1 upvotes, #46 of 2026-04-14
  47. ATANT: An Evaluation Framework for AI Continuity 1 upvotes, #46 of 2026-04-14
  48. SHARE: Social-Humanities AI for Research and Education 1 upvotes, #46 of 2026-04-14

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.