Daily Papers of 2025-04-09
- OmniSVG: A Unified Scalable Vector Graphics Generation Model 141 upvotes, #1 of 2025-04-09
- Hogwild! Inference: Parallel LLM Generation via Concurrent Attention 98 upvotes, #2 of 2025-04-09
- Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought 77 upvotes, #3 of 2025-04-09
- An Empirical Study of GPT-4o Image Generation Capabilities 59 upvotes, #4 of 2025-04-09
- COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values 41 upvotes, #5 of 2025-04-09
- Less-to-More Generalization: Unlocking More Controllability by In-Context Generation 33 upvotes, #6 of 2025-04-09
- Generative Evaluation of Complex Reasoning in Large Language Models 12 upvotes, #7 of 2025-04-09
- HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference 12 upvotes, #7 of 2025-04-09
- V-MAGE: A Game Evaluation Framework for Assessing Visual-Centric Capabilities in Multimodal Large Language Models 12 upvotes, #7 of 2025-04-09
- Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence 11 upvotes, #10 of 2025-04-09
- Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model 11 upvotes, #10 of 2025-04-09
- HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance 11 upvotes, #10 of 2025-04-09
- SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills 11 upvotes, #10 of 2025-04-09
- Efficient Reinforcement Finetuning via Adaptive Curriculum Learning 9 upvotes, #14 of 2025-04-09
- CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation 8 upvotes, #15 of 2025-04-09
- Leanabell-Prover: Posttraining Scaling in Formal Reasoning 6 upvotes, #16 of 2025-04-09
- Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets 3 upvotes, #17 of 2025-04-09
- ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery 1 upvotes, #18 of 2025-04-09
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.