Daily Papers of 2025-03-11

  1. Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders 212 upvotes, #1 of 2025-03-11
  2. SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models 63 upvotes, #2 of 2025-03-11
  3. MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning 53 upvotes, #3 of 2025-03-11
  4. Automated Movie Generation via Multi-Agent CoT Planning 40 upvotes, #4 of 2025-03-11
  5. Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning 37 upvotes, #5 of 2025-03-11
  6. VACE: All-in-One Video Creation and Editing 37 upvotes, #5 of 2025-03-11
  7. FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates 28 upvotes, #7 of 2025-03-11
  8. DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs 27 upvotes, #8 of 2025-03-11
  9. EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer 24 upvotes, #9 of 2025-03-11
  10. Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models 22 upvotes, #10 of 2025-03-11
  11. Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning 20 upvotes, #11 of 2025-03-11
  12. AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning 19 upvotes, #12 of 2025-03-11
  13. FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation 18 upvotes, #13 of 2025-03-11
  14. WritingBench: A Comprehensive Benchmark for Generative Writing 16 upvotes, #14 of 2025-03-11
  15. SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing 15 upvotes, #15 of 2025-03-11
  16. Unleashing the Potential of Large Language Models for Text-to-Image Generation through Autoregressive Representation Alignment 15 upvotes, #15 of 2025-03-11
  17. Agent models: Internalizing Chain-of-Action Generation into Reasoning models 14 upvotes, #17 of 2025-03-11
  18. MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning 14 upvotes, #17 of 2025-03-11
  19. DreamRelation: Relation-Centric Video Customization 13 upvotes, #19 of 2025-03-11
  20. LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning 12 upvotes, #20 of 2025-03-11
  21. Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement 9 upvotes, #21 of 2025-03-11
  22. Effective and Efficient Masked Image Generation Models 9 upvotes, #21 of 2025-03-11
  23. Words or Vision: Do Vision-Language Models Have Blind Faith in Text? 8 upvotes, #23 of 2025-03-11
  24. PE3R: Perception-Efficient 3D Reconstruction 8 upvotes, #23 of 2025-03-11
  25. This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs 7 upvotes, #25 of 2025-03-11
  26. State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models 5 upvotes, #26 of 2025-03-11
  27. BlackGoose Rimer: Harnessing RWKV-7 as a Simple yet Superior Replacement for Transformers in Large-Scale Time Series Modeling 5 upvotes, #26 of 2025-03-11
  28. YOLOE: Real-Time Seeing Anything 5 upvotes, #26 of 2025-03-11
  29. Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations 4 upvotes, #29 of 2025-03-11
  30. DiffCLIP: Differential Attention Meets CLIP 4 upvotes, #29 of 2025-03-11
  31. WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation 4 upvotes, #29 of 2025-03-11
  32. Efficient Distillation of Classifier-Free Guidance using Adapters 4 upvotes, #29 of 2025-03-11
  33. Detection Avoidance Techniques for Large Language Models 4 upvotes, #29 of 2025-03-11
  34. Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries 3 upvotes, #34 of 2025-03-11
  35. What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization 3 upvotes, #34 of 2025-03-11
  36. ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks 3 upvotes, #34 of 2025-03-11
  37. Should VLMs be Pre-trained with Image Data? 3 upvotes, #34 of 2025-03-11
  38. Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces 2 upvotes, #38 of 2025-03-11
  39. Novel Object 6D Pose Estimation with a Single Reference View 2 upvotes, #38 of 2025-03-11
  40. Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model 2 upvotes, #38 of 2025-03-11
  41. Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs 2 upvotes, #38 of 2025-03-11
  42. A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning 2 upvotes, #38 of 2025-03-11
  43. TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models 2 upvotes, #38 of 2025-03-11
  44. REF-VLM: Triplet-Based Referring Paradigm for Unified Visual Decoding 2 upvotes, #38 of 2025-03-11
  45. HumanMM: Global Human Motion Recovery from Multi-shot Videos 2 upvotes, #38 of 2025-03-11
  46. Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts 1 upvotes, #46 of 2025-03-11
  47. NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection 1 upvotes, #46 of 2025-03-11
  48. PhiloBERTA: A Transformer-Based Cross-Lingual Analysis of Greek and Latin Lexicons 1 upvotes, #46 of 2025-03-11
  49. Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning 1 upvotes, #46 of 2025-03-11
  50. RePO: ReLU-based Preference Optimization 1 upvotes, #46 of 2025-03-11

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.