siyeng feng

siyengfeng's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 5 papers about 21 hours ago

Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Enhancement Protocol

Paper • 2503.05860 • Published 6 days ago • 6

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Paper • 2503.07572 • Published 3 days ago • 25

Implicit Reasoning in Transformers is Reasoning through Shortcuts

Paper • 2503.07604 • Published 3 days ago • 17

Gemini Embedding: Generalizable Embeddings from Gemini

Paper • 2503.07891 • Published 3 days ago • 22

LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Paper • 2503.07536 • Published 3 days ago • 62

upvoted 4 papers 1 day ago

State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models

Paper • 2503.03499 • Published 8 days ago • 5

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Paper • 2503.06749 • Published 4 days ago • 20

FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation

Paper • 2503.06680 • Published 4 days ago • 17

Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning

Paper • 2503.07002 • Published 3 days ago • 36

upvoted 6 papers 3 days ago

An Empirical Study on Eliciting and Improving R1-like Reasoning Models

Paper • 2503.04548 • Published 7 days ago • 8

TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation

Paper • 2503.04872 • Published 7 days ago • 14

Learning from Failures in Multi-Attempt Reinforcement Learning

Paper • 2503.04808 • Published 9 days ago • 15

R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

Paper • 2503.05592 • Published 6 days ago • 24

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Paper • 2503.05132 • Published 6 days ago • 44

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching

Paper • 2503.05179 • Published 6 days ago • 42

upvoted a paper 5 days ago

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published 7 days ago • 76

upvoted 4 papers 6 days ago

Dedicated Feedback and Edit Models Empower Inference-Time Scaling for Open-Ended General-Domain Tasks

Paper • 2503.04378 • Published 7 days ago • 6

FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion

Paper • 2503.04222 • Published 7 days ago • 12

LINGOLY-TOO: Disentangling Memorisation from Reasoning with Linguistic Templatisation and Orthographic Obfuscation

Paper • 2503.02972 • Published 9 days ago • 23

START: Self-taught Reasoner with Tools

Paper • 2503.04625 • Published 7 days ago • 83