Get started
Author

Mohit Bansal

Observed name: Bansal, Mohit
ORCID: 0009-0009-2965-5354
Observed ORCID: 0009-0009-2965-5354
OpenAlex ID: A5125980650
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
2026 · Yu, Shoubin, Zhang, Yue, et al. · arXiv (Cornell University) · 2
PDF
AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
2026 · Zun Wang, Han Lin, et al. · Lecture notes in computer science · 2
PDF
MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
2026 · Fan, Yuxuan, Seo, Gyusik, et al. · arXiv (Cornell University) · 1
PDF
Deepfake-Agent: Aggregating Semantic Forgery Clues for Generalizable Detection
2026 · Xiao Guo, Yue Zhang, et al. · 1
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
2026 · Huang, Yidong, Wang, Zun, et al. · arXiv (Cornell University) · 1
PDF
EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
2026 · Wang, Ziyang, Zhang, Yue, et al. · arXiv (Cornell University) · 1
PDF
A Novel Approach to Evaluating the Effectiveness of Large Language Models for Multimodal Analysis of Embodied Learning in Classrooms
2026 · Joyce Horn Fonteles, Nithin Sivakumaran, et al. · International Conference on Learning Analytics and Knowledge (LAK) · 1
Multimodal Fact-Level Attribution for Verifiable Reasoning
2026 · Wan, David, Wang, Han, et al. · arXiv (Cornell University) · 1
PDF
Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
2026 · Nguyen, Duy, Xiao, Hanqi, et al. · arXiv (Cornell University) · 1
PDF
Representing the Unseen: Rethinking Visual Imagination for Spatial Reasoning
2026 · Zhao, Zengqi, Wang, Zun, et al. · arXiv (Cornell University)
PDF
MiRL: Error-Targeted Reinforcement Learning for Correcting Terminal Agent Misbehaviors
2026 · Tian, Runchu, Khan, Zaid, et al. · arXiv (Cornell University)
PDF
ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination
2026 · Sivakumaran, Nithin, Payani, Ali, et al. · arXiv (Cornell University)
PDF
From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents
2026 · Zhang, Yue, Lin, Han, et al. · arXiv (Cornell University)
PDF
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
2026 · Lee, Wonjun, Yang, Kyungsik, et al. · arXiv (Cornell University)
PDF
CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity
2026 · Sahu, Ananya, Bansal, Mohit, et al. · arXiv (Cornell University)
PDF
JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles
2026 · Li, Shawn, Yang, Wei, et al. · arXiv (Cornell University)
PDF
Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
2026 · Ziyang Wang, Honglu Zhou, et al.
GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization
2026 · Khan, Zaid, Chen, Justin Chih-Yao, et al. · arXiv (Cornell University)
PDF
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
2026 · Zhang, Yue, Wang, Zun, et al. · arXiv (Cornell University)
PDF
STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models
2026 · Liang, Yiming, Chen, Yixiao, et al. · arXiv (Cornell University)
PDF
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
2026 · Lee, Hyunji, Chen, Justin Chih-Yao, et al. · arXiv (Cornell University)
PDF
MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments
2026 · Wang, Han, Wan, David, et al. · arXiv (Cornell University)
PDF
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
2026 · Xiao, Hanqi, Patil, Vaidehi, et al. · arXiv (Cornell University)
PDF
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
2026 · Balasubramanian, Rishab, Lin, Pin-Jie, et al. · arXiv (Cornell University)
PDF
Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
2026 · Chen, Justin Chih-Yao, Prasad, Archiki, et al. · arXiv (Cornell University)
PDF
Works count: 32
Citation count: 11
H-index: 2
I10-index:
Year
Topic
Type