Морозов Егор

elmiller6's activity

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

upvoted a paper 2 days ago

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Paper • 2609.11115 • Published 8 days ago • 207

upvoted a paper 5 days ago

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

Paper • 2609.05463 • Published Aug 12 • 11

upvoted a paper 28 days ago

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

Paper • 2608.13558 • Published Aug 13 • 94

upvoted 2 papers about 1 month ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 171

Harness-G: A Graph-Structured Harness for Search Agents

Paper • 2607.27652 • Published Jul 30 • 6

upvoted 3 papers about 2 months ago

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Paper • 2607.25659 • Published Jul 28 • 86

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Paper • 2607.19191 • Published Jul 21 • 315

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Paper • 2607.17423 • Published Jul 19 • 168

upvoted 5 papers 2 months ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published Jul 16 • 214

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published Jul 16 • 173

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published Jul 14 • 110

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Paper • 2607.04033 • Published Jul 4 • 79

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published Jun 28 • 171

upvoted 6 papers 3 months ago

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Paper • 2607.02512 • Published Jul 2 • 310

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published May 28 • 255

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Paper • 2606.18023 • Published Jun 16 • 212

Looped World Models

Paper • 2606.18208 • Published Jun 16 • 489

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

Paper • 2606.11324 • Published Jun 9 • 174

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published Jun 8 • 490