Fangxu

ParadiseYu's activity

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

upvoted a paper 7 days ago

Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding

Paper • 2608.25356 • Published 8 days ago • 20

upvoted a paper 9 days ago

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published 10 days ago • 205

upvoted a collection 24 days ago

AudioRubrics

Collection

Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning: model and rubric dataset. • 2 items • Updated Jul 12 • 1

upvoted a paper 24 days ago

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

Paper • 2608.06867 • Published 27 days ago • 111

upvoted a paper 27 days ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published 28 days ago • 62

upvoted 6 papers 29 days ago

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory

Paper • 2509.04439 • Published Sep 4, 2025 • 2

TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning

Paper • 2510.03519 • Published Oct 3, 2025 • 1

FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse

Paper • 2606.11290 • Published Jun 9 • 2

ArrowGEV: Grounding Events in Video via Learning the Arrow of Time

Paper • 2601.06559 • Published Apr 16 • 1

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published Aug 3 • 183

Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning

Paper • 2608.02831 • Published Aug 3 • 15

upvoted 3 papers about 1 month ago

Visual Contrastive Self-Distillation

Paper • 2607.21556 • Published Jul 23 • 52

Weak-to-Strong On-Policy Distillation

Paper • 2607.26246 • Published Jul 28 • 58

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 513

upvoted an article about 1 month ago

view article

Article

Distillation in 2026 (so far): which frontier models use it and how

• 

sergiopaniego

•

Jul 8

• 21

upvoted a paper about 2 months ago

TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning

Paper • 2607.08940 • Published Jul 9 • 2

upvoted a paper 4 months ago

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Paper • 2605.17672 • Published May 17 • 23

upvoted a paper 5 months ago

When AI Navigates the Fog of War

Paper • 2603.16642 • Published Mar 17 • 32

upvoted 2 papers 7 months ago

Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens

Paper • 2602.10229 • Published Feb 10 • 5

Quantifying the Gap between Understanding and Generation within Unified Multimodal Models

Paper • 2602.02140 • Published Feb 2 • 12