Daily Papers of 2024-10-03

  1. RATIONALYST: Pre-training Process-Supervision for Improving Reasoning 34 upvotes, #1 of 2024-10-03
  2. PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation 31 upvotes, #2 of 2024-10-03
  3. From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging 30 upvotes, #3 of 2024-10-03
  4. Not All LLM Reasoners Are Created Equal 25 upvotes, #4 of 2024-10-03
  5. LEOPARD : A Vision Language Model For Text-Rich Multi-Image Tasks 23 upvotes, #5 of 2024-10-03
  6. Selective Aggregation for Low-Rank Adaptation in Federated Learning 18 upvotes, #6 of 2024-10-03
  7. Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis 15 upvotes, #7 of 2024-10-03
  8. ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation 15 upvotes, #7 of 2024-10-03
  9. MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages 14 upvotes, #9 of 2024-10-03
  10. 3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection 14 upvotes, #9 of 2024-10-03
  11. Quantifying Generalization Complexity for Large Language Models 12 upvotes, #11 of 2024-10-03
  12. FactAlign: Long-form Factuality Alignment of Large Language Models 8 upvotes, #12 of 2024-10-03
  13. HelpSteer2-Preference: Complementing Ratings with Preferences 7 upvotes, #13 of 2024-10-03
  14. BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation 5 upvotes, #14 of 2024-10-03
  15. EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis 5 upvotes, #14 of 2024-10-03
  16. General Preference Modeling with Preference Representations for Aligning Language Models 5 upvotes, #14 of 2024-10-03
  17. E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding 4 upvotes, #17 of 2024-10-03
  18. VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data 4 upvotes, #17 of 2024-10-03
  19. EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control 4 upvotes, #17 of 2024-10-03
  20. HarmoniCa: Harmonizing Training and Inference for Better Feature Cache in Diffusion Transformer Acceleration 4 upvotes, #17 of 2024-10-03
  21. Old Optimizer, New Norm: An Anthology 3 upvotes, #21 of 2024-10-03
  22. Closed-loop Long-horizon Robotic Planning via Equilibrium Sequence Modeling 3 upvotes, #21 of 2024-10-03
  23. SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios 2 upvotes, #23 of 2024-10-03
  24. InfiniPot: Infinite Context Processing on Memory-Constrained LLMs 2 upvotes, #23 of 2024-10-03

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.