Learning Adaptive Parallel Reasoning with Language Models Paper • 2504.15466 • Published 17 days ago • 42
Describe Anything: Detailed Localized Image and Video Captioning Paper • 2504.16072 • Published 16 days ago • 60
Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling Paper • 2504.13169 • Published 21 days ago • 39
CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis Paper • 2503.23145 • Published Mar 29 • 34
Training Task Experts through Retrieval Based Distillation Paper • 2407.05463 • Published Jul 7, 2024 • 10