Ziyang Wang

I am a fourth year CS Ph.D. student at The University of North Carolina, Chapel Hill advised by Prof. Mohit Bansal and also work closely with Prof. Gedas Bertasius. My research interest is video‐language understanding and multimodal AI. Particularly, I am interested in the challenge of reasoning over long and complex videos. I am actively looking for internship position for 2026 summer, feel free to reach out!

Previously, I worked as a research intern at Salesforce in 2025 summer (manager: Dr. Juan Carlos Niebles). I worked as a research intern at Meta, FAIR Perception team in 2024 summer (managers: Dr. Ronghang Hu, and Dr. Christoph Feichtenhofer). Previously, I was an Applied Scientist Intern in Amazon Alexa AI working with Dr. Heba Elfardy, Dr. Kevin Small, Dr. Markus Dreyer. I also interned in Tsinghua AIR working with Prof. Jingjing Liu. I finished my undergrad study at UESTC and advised by Prof. Jingjing Li.

My email address is ziyangw at cs . unc . edu, if you have any questions, feel free to contact me!

Google Scholar  /  Curriculum Vitae  /  GitHub  /  Linkedin

Research

In general, I am interested in the fundamental challenges in video-language understanding. I have been working on multiple projects that aim to understand and reason over long and complex videos, including Agentic approach (VideoTree, CVPR 2025), RL + Test-time scaling (Video-RTS EMNLP 2025), LLM-based understanding (LLoVi, Mexa,... EMNLP 2024/2025) and coarse-to-fine alignments (UcoFiA ICCV2023).

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning

We introduce Video-RTS, a new approach to improve video reasoning capability with drastically improved data efficiency by combining data-efficient RL with a video-adaptive test-time scaling (TTS) strategy.

MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation

We introduce MEXA, a training-free framework that performs modality- and task-aware aggregation of multiple expert models to enable effective multimodal reasoning across diverse and distinct domains.

SiLVR: A Simple Language-based Video Reasoning Framework

We present SiLVR, a Simple Language-based Video Reasoning framework that decomposes complex video understanding into two stages. In the first stage, SiLVR transforms raw video into language-based representations using multisensory inputs, such as short clip captions and audio/speech subtitles. In the second stage, language descriptions are fed into a powerful reasoning LLM to solve complex video-language understanding tasks. SiLVR has been awarded the 1st in Track 1B: Multi-Discipline Lecture Understanding at CVPR 2025 Multimodal Video Agent Workshop

TimeRefine: Temporal Grounding with Time Refining Video LLM

In this work, we propose TimeRefine to enhance the capability of Video LLMs in performing temporal grounding. Unlike previous approaches that focus on data curation or architectural enhancements, we focus on refining the learning objective to better suit temporal grounding within the Video LLM framework.

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

We introduce VideoTree, a query-adaptive and hierarchical framework for long-video understanding with LLMs. Specifically, VideoTree dynamically extracts query-related information from the input video and builds a tree-based video representation for LLM reasoning.

DAM: Dynamic Adapter Merging for Continual Video QA Learning

In this work, we investigate the challenging and relatively unexplored problem of rehearsal-free domain-incremental VidQA learning. Our proposed DAM framework outperforms existing state-of-the-art by 9.1% with 1.9% less forgetting on a benchmark with six distinct video domains.

Unified Embeddings for Multimodal Retrieval via Frozen LLMs

In this work, We present Unified Embeddings for Multimodal Retrieval (UNIMUR), a simple but effective approach that embeds multimodal inputs and retrieves visual and textual outputs via frozen Large Language Models (LLMs). Specifically, UNIMUR jointly retrieves multimodal outputs via unified multimodal embedding and applies dual alignment training to account for both visual and textual semantics.

A Simple LLM Framework for Long-Range Video Question-Answering

We present LLoVi, a language-based framework for long-range video question-answering (LVQA). Unlike prior long-range video understanding methods, which are often costly and require specialized long-range video modeling design (e.g., memory queues, state-space layers, etc.), our approach uses a frame/clip-level visual captioner coupled with a Large Language Model (GPT-3.5, GPT-4) leading to a simple yet surprisingly effective LVQA framework.

Unified Coarse-to-Fine Alignment for Video-Text Retrieval

UCoFiA captures the cross-modal similarity information at different granularity levels(video-sentence, frame-sentence, pixel-word) and unifies multi-level alignments for video-text retrieval.

Language-Augmented Pixel Embedding for Generalized Zero-shot Learning

In this paper, we propose a novel GZSL framework named Language-Augmented Pixel Embedding (LAPE), which directly maps the image pixels to the semantic attributes with cross-modal guidance.

Region Semantically Aligned Network for Zero-Shot Learning

We propose a novel ZSL framework named Region Semantically Aligned Network (RSAN), which transfers region-attribute alignment from seen classes to unseen classes.

Hobby

I am a die-heart Arsenal and Tar Heel fan.

Design and source code from Leonid Keselman's website, thanks!