Mubarak Shah

Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach

Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks

The Telephone Game: Evaluating Semantic Drift in Unified Models

Repair Aware Forgetting: An Iterative Approach to Unlearning in T2I Diffusion Models

Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding

Cross-View Open-Vocabulary Object Detection in Aerial Imagery

StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales

Multi-Level Multi-Turn RL Outperforms GRPO: Reasoning with Textual Feedback

CompLLM: Compression for Long Context Q&A

Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety

From Frames to Clips: Efficient Key Clip Selection for Long-Form Video Understanding

MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark

Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models via Distributional Regularization

ImplicitQA: Going beyond frames towards Implicit Video Reasoning

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents

DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models

MGD$^3$ : Mode-Guided Dataset Distillation using Diffusion Models

Exploring Local Memorization in Diffusion Models via Bright Ending Attention

ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks

ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition

AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation

AnyView: Few Shot Personalized View Transfer

Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention

Hierarchical Preference Optimization: Learning to achieve goals via feasible subgoals prediction

Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning

GeoTimeCLIP: Unveiling the When and Where of Images

MGD$^3$: Mode-Guided Dataset Distillation using Diffusion Models

LIAR: Leveraging Inverse Alignment to Jailbreak LLMs in Seconds

StretchySnake: Flexible VideoMamba for Short and Long-Form Action Recognition

DIPPER: Direct Preference Optimization for Primitive-Enabled Hierarchical Reinforcement Learning

Self-supervised Privacy-preservation via Latent Anonymization for Generalizable Video Understanding

Investigating Memorization in Video Diffusion Models

BrailleVision: Text Instruction Tuning of LLMs to Improve Visual Skills