Xin Xu

XinXuNLPer's activity

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

upvoted 2 papers about 1 month ago

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published Feb 15 • 57

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

Paper • 2608.20202 • Published Aug 20 • 34

authored a paper about 1 month ago

Evaluating Music Context Preservation: A Multi-facet Framework for Music Editing Systems

Paper • 2512.14629 • Published Aug 18 • 3

submitted a paper to Daily Papers about 1 month ago

Evaluating Music Context Preservation: A Multi-facet Framework for Music Editing Systems

Paper • 2512.14629 • Published Aug 18 • 3

upvoted a paper about 1 month ago

Evaluating Music Context Preservation: A Multi-facet Framework for Music Editing Systems

Paper • 2512.14629 • Published Aug 18 • 3

authored 3 papers about 2 months ago

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

Paper • 2608.12036 • Published Aug 12 • 89

CSyMR: Benchmarking Compositional Music Information Retrieval in Symbolic Music Reasoning

Paper • 2601.11556 • Published Feb 27

Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning

Paper • 2606.03965 • Published Jun 2 • 1

upvoted 2 articles about 2 months ago

view article

Article

Beyond Surface Alignment: Belief as the Gateway to Deep Alignment in LLMs

• 

Alibaba-VELLDEPTH

•

Aug 3

• 5

view article

Article

超越表层对齐：信念是通往深层对齐的新入口

• 

Alibaba-VELLDEPTH

•

Aug 3

• 12

upvoted a paper about 2 months ago

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

Paper • 2608.12036 • Published Aug 12 • 89

upvoted a paper 3 months ago

LightMem-Ego: Your AI Memory for Everyday Life

Paper • 2607.11487 • Published Jul 13 • 45

upvoted 2 papers 4 months ago

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

Paper • 2606.13578 • Published Jun 11 • 62

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models

Paper • 2605.30219 • Published May 28 • 23

upvoted 3 papers 5 months ago

Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling

Paper • 2604.27039 • Published Apr 29 • 25

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis

Paper • 2604.24198 • Published Apr 27 • 24

Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language

Paper • 2604.19667 • Published Apr 21 • 21

upvoted 2 papers 6 months ago

LightThinker++: From Reasoning Compression to Memory Management

Paper • 2604.03679 • Published Apr 4 • 36

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders

Paper • 2602.05027 • Published Feb 4 • 63

liked a model 7 months ago

slseanwu/MIDI-LLM_Llama-3.2-1B

Text-to-Audio • 2B • Updated Jul 27 • 6.52k • 37