Mitigating Overthinking through Reasoning Shaping
Paper
•
2510.09535
•
Published
•
5
Shaohang Wei
SylvainWei
AI & ML interests
NLP, LLM
Recent Activity
upvoted
a
paper
5 days ago
MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents
liked
a model
7 days ago
mwhanna/qwen3-1.7b-transcoders-lowl0
upvoted
a
paper
14 days ago
MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era
Organizations
authored
a
paper
4 months ago
authored
4
papers
8 months ago
Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
Paper
•
2506.07434
•
Published
•
7
TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
Paper
•
2505.12891
•
Published
•
10
MeNTi: Bridging Medical Calculator and LLM Agent with Nested Tool Calling
Paper
•
2410.13610
•
Published
Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation
Paper
•
2503.08057
•
Published