collaborators

5 papers

cs.CL2026

DLLG: Dynamic Logit-Level Gating of LLM Experts

Bingnan Li, Zhaoyang Zhang, Xiaoze Liu +6

Leveraging multiple specialized LLMs can combine complementary strengths, but existing approaches trade adaptability for stability: routing commits prematurely, heuristic ensemblin…

cs.CV2026

Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

Jing Tan, Zhaoyang Zhang, Yantao Shen +6

We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects…

cs.CV2024

Efficient Scaling of Diffusion Transformers for Text-to-Image Generation

Hao Li, Shamit Lal, Zhiheng Li +9

We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training…

cs.CV2024

DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models

Sungnyun Kim, Haofu Liao, Srikar Appalaraju +6

Visual document understanding (VDU) is a challenging task that involves understanding documents across various modalities (text and image) and layouts (forms, tables, etc.). This s…

cs.CV2024

Open-World Dynamic Prompt and Continual Visual Representation Learning

Youngeun Kim, Jun Fang, Qin Zhang +7

The open world is inherently dynamic, characterized by ever-evolving concepts and distributions. Continual learning (CL) in this dynamic open-world environment presents a significa…