배가은

hudsonlewis

·

AI & ML interests

Alignment-focused model research. Building practical tools.

Recent Activity

liked a dataset 1 day ago

electricsheepafrica/africa-ghana-trend-in-road-accidents-and-casualties-b5cbd8a8

liked a model 1 day ago

nvidia/Qwen3.6-35B-A3B-NVFP4

liked a dataset 3 days ago

born5149/autonomous-vehicle-sensor-fusion

View all activity

Organizations

None yet

upvoted 3 papers 4 days ago

X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras

Paper • 2607.12993 • Published 6 days ago • 131

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published 6 days ago • 201

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

Paper • 2607.08741 • Published 11 days ago • 11

upvoted a paper 12 days ago

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published 13 days ago • 94

upvoted 2 papers 14 days ago

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

Paper • 2606.29526 • Published 22 days ago • 168

SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE

Paper • 2606.32033 • Published 20 days ago • 7

upvoted a paper 17 days ago

Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE

Paper • 2606.26938 • Published 25 days ago • 6

upvoted a paper 27 days ago

OpenRath: Session-Centered Runtime State for Agent Systems

Paper • 2606.19409 • Published Jun 17 • 78

upvoted 4 papers about 2 months ago

One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation

Paper • 2605.29429 • Published May 28 • 8

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Paper • 2606.02437 • Published Jun 1 • 239

Trust-Region Behavior Blending for On-Policy Distillation

Paper • 2605.31159 • Published May 29 • 69

How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning

Paper • 2605.27310 • Published May 26 • 20

upvoted a paper 2 months ago

SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise

Paper • 2602.12783 • Published Feb 13 • 246

upvoted 3 papers 4 months ago

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Paper • 2603.25746 • Published Mar 26 • 155

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published Mar 15 • 432

SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models

Paper • 2603.16859 • Published Mar 17 • 248