Daily Papers of 2024-10-11

  1. WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents 48 upvotes, #1 of 2024-10-11
  2. MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code 44 upvotes, #2 of 2024-10-11
  3. MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents 32 upvotes, #3 of 2024-10-11
  4. PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs 29 upvotes, #4 of 2024-10-11
  5. Agent S: An Open Agentic Framework that Uses Computers Like a Human 24 upvotes, #5 of 2024-10-11
  6. DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation 23 upvotes, #6 of 2024-10-11
  7. Benchmarking Agentic Workflow Generation 22 upvotes, #7 of 2024-10-11
  8. DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models 17 upvotes, #8 of 2024-10-11
  9. Intriguing Properties of Large Language and Vision Models 16 upvotes, #9 of 2024-10-11
  10. Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow 16 upvotes, #9 of 2024-10-11
  11. GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models 15 upvotes, #11 of 2024-10-11
  12. Progressive Autoregressive Video Diffusion Models 15 upvotes, #11 of 2024-10-11
  13. Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality 10 upvotes, #13 of 2024-10-11
  14. Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition 10 upvotes, #13 of 2024-10-11
  15. Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning 9 upvotes, #15 of 2024-10-11
  16. SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe 8 upvotes, #16 of 2024-10-11
  17. Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations 8 upvotes, #16 of 2024-10-11
  18. Emergent properties with repeated examples 7 upvotes, #18 of 2024-10-11
  19. Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System 7 upvotes, #18 of 2024-10-11
  20. Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates 6 upvotes, #20 of 2024-10-11
  21. Accelerated Preference Optimization for Large Language Model Alignment 4 upvotes, #21 of 2024-10-11
  22. Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models 3 upvotes, #22 of 2024-10-11
  23. Vector-ICL: In-context Learning with Continuous Vector Representations 3 upvotes, #22 of 2024-10-11
  24. MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting 3 upvotes, #22 of 2024-10-11
  25. Zebra: In-Context and Generative Pretraining for Solving Parametric PDEs 2 upvotes, #25 of 2024-10-11
  26. LPZero: Language Model Zero-cost Proxy Search from Zero 2 upvotes, #25 of 2024-10-11

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.