AI.info
Mohit Bansal
Explore Mohit Bansal on AI.info.
- CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity
- Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA
- Multimodal Fact-Level Attribution for Verifiable Reasoning
- Effective Reasoning Chains Reduce Intrinsic Dimensionality
- Reliable and Responsible Foundation Models: A Comprehensive Survey
- Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
- Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
- Hierarchy-Aware Multimodal Unlearning for Medical AI
- DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
- Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
- StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
- PRInTS: Reward Modeling for Long-Horizon Information Seeking
- Error-Driven Scene Editing for 3D Grounding in Large Language Models
- PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise
- PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions
- One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration