Patricia Miller

Kestrel-Rin's activity

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

upvoted a paper 12 days ago

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

Paper • 2610.12341 • Published 16 days ago • 50

upvoted a paper 21 days ago

Scaling and Distilling Text Embeddings for Better Diffusibility

Paper • 2610.01016 • Published 23 days ago • 58

upvoted 3 papers about 1 month ago

JEPA-Anything: Learning Predictive Models across Different Worlds

Paper • 2609.20800 • Published Sep 17 • 79

Region-Level Policy Optimization for Fine-grained MLLM Perception

Paper • 2609.19745 • Published Sep 17 • 41

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 483

upvoted 3 papers about 2 months ago

WorldReward: Reward Modeling for Camera-Conditioned World Models

Paper • 2609.03952 • Published Sep 3 • 28

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

Paper • 2609.04083 • Published Sep 3 • 25

LatentPress: Context Compression Beyond Text and Vision

Paper • 2609.01507 • Published Sep 1 • 83

upvoted 3 papers 2 months ago

LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation

Paper • 2608.12990 • Published Aug 13 • 14

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Paper • 2608.00677 • Published Aug 1 • 263

SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification

Paper • 2608.08786 • Published Aug 9 • 6

upvoted 4 papers 3 months ago

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

Paper • 2608.03979 • Published Aug 4 • 36

MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations

Paper • 2607.28956 • Published Jul 31 • 114

Poplar: A Scalable Pipeline for Human-Centric Image Dataset Synthesis

Paper • 2608.00440 • Published Aug 1 • 11

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published Jul 26 • 96