Mohit Bansal

mohitbansal

AI & ML interests

LLM, Transformers

Recent Activity

authored a paper 3 days ago

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

authored a paper 11 days ago

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems

authored a paper about 2 months ago

Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning

View all activity

Organizations

None yet

mohitbansal's activity

authored a paper 3 days ago

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Paper • 2504.15485 • Published 4 days ago • 5

authored a paper 11 days ago

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems

Paper • 2504.09763 • Published 12 days ago • 13

authored a paper about 2 months ago

Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning

Paper • 2503.05641 • Published Mar 7 • 2

authored a paper 2 months ago

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning

Paper • 2502.15082 • Published Feb 20 • 1

authored a paper 3 months ago

Learning to Generate Unit Tests for Automated Debugging

Paper • 2502.01619 • Published Feb 3 • 4

authored 2 papers 4 months ago

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

Paper • 2412.08467 • Published Dec 11, 2024 • 5

SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts

Paper • 2412.05552 • Published Dec 7, 2024 • 5

authored 2 papers 5 months ago

Reverse Thinking Makes LLMs Stronger Reasoners

Paper • 2411.19865 • Published Nov 29, 2024 • 23

DreamRunner: Fine-Grained Storytelling Video Generation with Retrieval-Augmented Motion Adaptation

Paper • 2411.16657 • Published Nov 25, 2024 • 19

authored a paper 6 months ago

Unbounded: A Generative Infinite Game of Character Life Simulation

Paper • 2410.18975 • Published Oct 24, 2024 • 38

authored a paper 7 months ago

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints

Paper • 2410.06458 • Published Oct 9, 2024 • 8

updated a collection 11 months ago

Fast Ai

Collection

1 item • Updated Jun 3, 2024

updated a model 11 months ago

mohitbansal/gradio_pets

Updated Jun 3, 2024