Zhenyi Shen

zen-E's activity

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

upvoted a collection about 21 hours ago

PLatour

Collection

PLatour: 30 Qwen3/Qwen3.5 inference models and 3 datasets. Paper: https://arxiv.org/abs/2611.06976 • 33 items • Updated 6 days ago • 1

upvoted 4 papers 3 days ago

Stabilizing Temporal Inference Dynamics for Online Surgical Phase Recognition

Paper • 2605.16387 • Published May 11 • 2

Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding

Paper • 2602.06161 • Published Feb 5 • 5

EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Grading

Paper • 2606.06350 • Published Jun 4 • 1

EnvLunch: The Environment as a Free Lunch for Learning to Interact

Paper • 2610.33817 • Published 20 days ago • 4

upvoted a paper 6 days ago

On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer

Paper • 2611.06976 • Published 8 days ago • 16

upvoted a paper 29 days ago

Self-Distillation with Verbal Regularization

Paper • 2610.16354 • Published Oct 12 • 25

upvoted an article about 1 month ago

view article

Article

大模型的记忆管理：从记忆外挂到主动管理

• 

Junrulu

•

Oct 9

• 3

upvoted 2 papers 2 months ago

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

Paper • 2608.28476 • Published Aug 28 • 32

Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge

Paper • 2608.28478 • Published Aug 28 • 19

upvoted 2 papers 5 months ago

Large Language Models Hack Rewards, and Society

Paper • 2606.04075 • Published Jun 2 • 11

Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs

Paper • 2605.30501 • Published May 28 • 27

upvoted 3 papers 6 months ago

Toward Native Multimodal Modeling: A Roadmap

Paper • 2605.25343 • Published May 25 • 40

Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis

Paper • 2605.18451 • Published May 18 • 41

Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models

Paper • 2604.27251 • Published Apr 29 • 9

upvoted a paper 7 months ago

Where does output diversity collapse in post-training?

Paper • 2604.16027 • Published Apr 17 • 21

upvoted a paper 8 months ago

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published Mar 10 • 152

upvoted 3 papers 9 months ago

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

Paper • 2511.20102 • Published Nov 25, 2025 • 29

Context Compression via Explicit Information Transmission

Paper • 2602.03784 • Published Feb 3 • 16

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

Paper • 2602.02007 • Published Feb 2 • 20