Yang's picture

Yang

jacklanda

·

AI & ML interests

Reasoning, Mech. Interp., Semantics

Recent Activity

authored a paper about 2 hours ago

Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs

authored a paper about 2 hours ago

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning

authored a paper about 2 hours ago

ICM-Fusion: In-Context Meta-Optimized LoRA Fusion for Multi-Task Adaptation

View all activity

Organizations

None yet

upvoted a paper about 5 hours ago

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning

Paper • 2512.07461 • Published about 24 hours ago • 38

upvoted 2 papers 6 months ago

Resa: Transparent Reasoning Models via SAEs

Paper • 2506.09967 • Published Jun 11 • 21

RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling

Paper • 2506.08672 • Published Jun 10 • 30

upvoted 2 papers 7 months ago

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Paper • 2505.13308 • Published May 19 • 27

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Paper • 2505.03335 • Published May 6 • 188

upvoted a paper 8 months ago

OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts

Paper • 2503.22952 • Published Mar 29 • 17

upvoted 3 papers over 1 year ago

CCAE: A Corpus of Chinese-based Asian Englishes

Paper • 2310.05381 • Published Oct 9, 2023 • 1

Revisiting a Pain in the Neck: Semantic Phrase Processing Benchmark for Language Models

Paper • 2405.02861 • Published May 5, 2024 • 1

MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models

Paper • 2308.09729 • Published Aug 17, 2023 • 6

upvoted an article over 1 year ago

Article

Fine-tuning Llama 2 70B using PyTorch FSDP

+2

Sep 13, 2023

•

31