Junrulu

Junrulu's activity

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

upvoted 3 papers 5 days ago

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

Paper • 2610.03509 • Published 17 days ago • 21

Self-Distillation with Verbal Regularization

Paper • 2610.16354 • Published 7 days ago • 40

DoSA: Dots Sparse Attention

Paper • 2610.13990 • Published 23 days ago • 80

upvoted 3 articles 9 days ago

view article

Article

大模型偏好优化技术：DPO及其变种

• 

Junrulu

•

Feb 20, 2025

• 22

view article

Article

结合Deepseek代码探讨MLA的改进及收益

• 

Junrulu

•

Feb 20, 2025

• 8

view article

Article

大模型的记忆管理：从记忆外挂到主动管理

• 

Junrulu

•

9 days ago

• 3

upvoted a paper 16 days ago

Who Thinks First? Designing Productive Friction with Engage-to-Unlock GenAI

Paper • 2610.01518 • Published 18 days ago • 1

upvoted a paper 19 days ago

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Paper • 2609.35457 • Published 21 days ago • 68

upvoted a collection about 1 month ago

RoleMRC

Collection

A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following • 6 items • Updated Sep 1 • 3

upvoted 2 papers about 2 months ago

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

Paper • 2608.28478 • Published Aug 28 • 20

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

Paper • 2608.28476 • Published Aug 28 • 31

upvoted 2 papers 3 months ago

DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents

Paper • 2608.00486 • Published Aug 1 • 16

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

Paper • 2607.20911 • Published Jul 23 • 25

upvoted a paper 4 months ago

From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI

Paper • 2606.14502 • Published Jun 12 • 118

upvoted 2 papers 5 months ago

Toward Native Multimodal Modeling: A Roadmap

Paper • 2605.25343 • Published May 25 • 41

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

Paper • 2605.18451 • Published May 18 • 41

upvoted a paper 7 months ago

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Paper • 2603.28458 • Published Mar 30 • 41

upvoted 2 papers 9 months ago

Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding

Paper • 2601.20430 • Published Jan 28 • 17

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

Paper • 2601.19798 • Published Jan 27 • 45

upvoted a collection 9 months ago

Youtu

Collection

13 items • Updated about 22 hours ago • 28