activity
20242026
collaborators

7 papers

cs.CV2026

PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards

Minh-Quan Le, Gaurav Mittal, Cheng Zhao +3

Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training…

cs.CV2025

Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation

Su Sun, Cheng Zhao, Himangi Mittal +4

Generating dynamic 4D objects from sparse inputs is difficult because it demands joint preservation of appearance and motion coherence across views and time while suppressing artif…

cs.CV2025

Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding

Yutao Tang, Cheng Zhao, Gaurav Mittal +4

Recent advances in 3D vision-language models (VLMs) highlight a strong potential for 3D scene understanding and reasoning. However, effectively tokenizing 3D scenes into holistic s…

cs.LG2025

Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter

Lei Jiang, Wen Ge, Niels Cariou-Kotlarek +6

Diffusion models have achieved state-of-the-art results in generative modelling but remain computationally intensive at inference time, often requiring thousands of discretization…

cs.CV2025

Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment

Minh-Quan Le, Gaurav Mittal, Tianjian Meng +5

While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Que…

cs.CV2025

DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos

Zijia Lu, A S M Iftekhar, Gaurav Mittal +6

Long Video Temporal Grounding (LVTG) aims at identifying specific moments within lengthy videos based on user-provided text queries for effective content retrieval. The approach ta…