Mohit Bansal

University of North Carolina at Chapel Hill — United States

Computer Science · Physical Sciences

61h-index19.4kcitations624works2.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(314), Natural Language Processing Techniques(256), Multimodal Machine Learning Applications(231), Domain Adaptation and Few-Shot Learning(68), Advanced Image and Video Retrieval Techniques(49)

Publications622 total

Hierarchy-Aware Multimodal Unlearning for Medical AI
arXiv (Cornell University)·2025Open Access
Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
arXiv (Cornell University)·2025Open Access
Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering
arXiv (Cornell University)·2025Open Access
Planning with Sketch-Guided Verification for Physics-Aware Video Generation
arXiv (Cornell University)·2025Open Access
PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise
arXiv (Cornell University)·2025Open Access
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
arXiv (Cornell University)·2025Open Access
SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models
arXiv (Cornell University)·2025Open Access
Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails
arXiv (Cornell University)·2025Open Access
VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
arXiv (Cornell University)·2025Open Access
RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation
arXiv (Cornell University)·2025Open Access
The mevalonate pathway couples lipid metabolism to amino acid synthesis via ubiquinone-dependent redox control
2025· 1 citedOpen Access
Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
arXiv (Cornell University)·2025Open Access
Accuracy and perforation rate of free-hand pedicle screw insertion in thoracic spine
The Egyptian Journal of Neurosurgery : the official publication of the Egyptian Society of Neurological Surgeons/Egyptian journal of neurosurgery·2025Open Access
Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
arXiv (Cornell University)·2025Open Access
Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact
arXiv (Cornell University)·2025Open Access
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
2025· 16 cited
CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval
arXiv (Cornell University)·2025Open Access
Movie Facts and Fibs (MF$^2$): A Benchmark for Long Movie Understanding
ArXiv.org·2025Open Access
CLATTER: Comprehensive Entailment Reasoning for Hallucination Detection
arXiv (Cornell University)·2025Open Access
Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
arXiv (Cornell University)·2025Open Access
page 1 of 32Next →

Frequent Co-authors

Tamara L. Berg(9), Licheng Yu(8), Kevin Gimpel(7), Hao Tan(6), Yixin Nie(6), Jie Lei(5), Karen Livescu(5), John Wieting(3), Hongyuan Mei(3), Matthew R. Walter(3), Jaemin Cho(3), Makoto Miwa(2), Zhe Lin(2), Xiaohui Shen(2), Shuicheng Yan(2), Yen-Chun Chen(2), Derek Tam(2), Colin Raffel(2), Jie Lei(2), Yicheng Wang(2)