University of Washington

Verified

https://www.washington.edu

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

weikaih authored a paper 1 day ago

ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models

weikaih authored a paper 1 day ago

m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks

weikaih authored a paper 1 day ago

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

View all activity

Papers

Micro Language Models Enable Instant Responses

You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass

View all Papers

submitted a paper to Daily Papers 16 days ago

Micro Language Models Enable Instant Responses

Paper • 2604.19642 • Published 18 days ago • 3

submitted a paper to Daily Papers 24 days ago

You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass

Paper • 2604.10966 • Published 26 days ago • 11

authored 2 papers about 1 month ago

CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation

Paper • 2602.18424 • Published Feb 20

PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning

Paper • 2603.26653 • Published Mar 27 • 18

submitted a paper to Daily Papers about 1 month ago

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models

Paper • 2603.24575 • Published Mar 25 • 18

updated a collection about 2 months ago

SuperBPE

SuperBPE tokenizers and models trained with them • 8 items • Updated Mar 23 • 17

submitted a paper to Daily Papers about 2 months ago

COMIC: Agentic Sketch Comedy Generation

Paper • 2603.11048 • Published Mar 11 • 4

submitted a paper to Daily Papers 2 months ago

Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos

Paper • 2602.23543 • Published Feb 26 • 9

submitted a paper to Daily Papers 4 months ago

Patient-Similarity Cohort Reasoning in Clinical Text-to-SQL

Paper • 2601.09876 • Published Jan 14 • 7

updated a collection 4 months ago

SuperBPE

SuperBPE tokenizers and models trained with them • 8 items • Updated Mar 23 • 17

authored a paper 5 months ago

Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation

Paper • 2512.11792 • Published Dec 12, 2025 • 10

authored 3 papers 5 months ago

LlamaFusion: Adapting Pretrained Language Models for Multimodal Generation

Paper • 2412.15188 • Published Dec 19, 2024 • 2

MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation

Paper • 2506.07999 • Published Jun 9, 2025 • 2

TV2TV: A Unified Framework for Interleaved Language and Video Generation

Paper • 2512.05103 • Published Dec 4, 2025 • 20

updated a collection 6 months ago

SuperBPE

SuperBPE tokenizers and models trained with them • 8 items • Updated Mar 23 • 17

updated a Space 7 months ago

README

published a Space 7 months ago

README

authored a paper 11 months ago

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL

Paper • 2505.23977 • Published May 29, 2025 • 10

in UW/OLMo2-8B-SuperBPE-t180k about 1 year ago

Training code for Tokenizer

#1 opened about 1 year ago by