AI研究論文デイリー

BitNet b1.58 2B4T Technical Report

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness

SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

Cobra: Efficient Line Art COlorization with BRoAder References

AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?

SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning

Robust and Fine-Grained Detection of AI Generated Texts

Towards Learning to Complete Anything in Lidar

Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting

Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution

BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian Splatting

FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents

"It's not a representation of me": Examining Accent Bias and Digital Exclusion in Synthetic AI Voice Services