Daily Papers of 2025-04-17

1. BitNet b1.58 2B4T Technical Report 66 upvotes, #1 of 2025-04-17
2. ReTool: Reinforcement Learning for Strategic Tool Use in LLMs 58 upvotes, #2 of 2025-04-17
3. ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness 45 upvotes, #3 of 2025-04-17
4. Cobra: Efficient Line Art COlorization with BRoAder References 27 upvotes, #4 of 2025-04-17
5. SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models 26 upvotes, #5 of 2025-04-17
6. AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference 25 upvotes, #6 of 2025-04-17
7. REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers 20 upvotes, #7 of 2025-04-17
8. MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges? 17 upvotes, #8 of 2025-04-17
9. SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning 16 upvotes, #9 of 2025-04-17
10. Robust and Fine-Grained Detection of AI Generated Texts 11 upvotes, #10 of 2025-04-17
11. Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution 10 upvotes, #11 of 2025-04-17
12. Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting 10 upvotes, #11 of 2025-04-17
13. Towards Learning to Complete Anything in Lidar 10 upvotes, #11 of 2025-04-17
14. BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian Splatting 7 upvotes, #14 of 2025-04-17
15. FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents 5 upvotes, #15 of 2025-04-17
16. "It's not a representation of me": Examining Accent Bias and Digital Exclusion in Synthetic AI Voice Services 4 upvotes, #16 of 2025-04-17

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.