Texas A&M University

university

Verified

https://www.tamu.edu

AI & ML interests

None defined yet.

Recent Activity

PardisTaghavi submitted a paper 4 days ago

Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models

Utkarsh-Mishra authored a paper about 1 month ago

Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping

Utkarsh-Mishra authored a paper about 1 month ago

Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

View all activity

Papers

Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models

OpenLongTail: Generative Scaling of Long-Tail Driving Data

View all Papers

submitted a paper to Daily Papers 4 days ago

Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models

Paper • 2608.18484 • Published 10 days ago • 9

authored a paper 17 days ago

Attention Sinks and Outliers in Attention Residuals

Paper • 2605.17887 • Published May 18

authored 2 papers about 1 month ago

Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping

Paper • 2510.09741 • Published Apr 20

Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

Paper • 2607.13429 • Published Jul 15 • 16

submitted a paper to Daily Papers about 1 month ago

OpenLongTail: Generative Scaling of Long-Tail Driving Data

Paper • 2607.09655 • Published Jul 10 • 5

authored a paper 3 months ago

When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning

Paper • 2605.26350 • Published May 25

submitted a paper to Daily Papers 5 months ago

Training a Student Expert via Semi-Supervised Foundation Model Distillation

Paper • 2604.03841 • Published Apr 4 • 11

vztu

submitted 2 papers to Daily Papers 5 months ago

The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics

Paper • 2603.14375 • Published Mar 15 • 20

SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation

Paper • 2603.16864 • Published Mar 17 • 18

submitted 2 papers to Daily Papers 6 months ago

NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving

Paper • 2603.07901 • Published Mar 9 • 5

Autophoresis of a Janus particle near a planar wall: a lubrication limit

Paper • 2603.00791 • Published Feb 28 • 1

authored a paper 6 months ago

City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs

Paper • 2512.15933 • Published Dec 17, 2025

vztu

submitted 2 papers to Daily Papers 7 months ago

PISCO: Precise Video Instance Insertion with Sparse Control

Paper • 2602.08277 • Published Feb 9 • 13

Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling

Paper • 2602.09084 • Published Feb 9 • 30

authored 2 papers 12 months ago

Fast and Low-Cost Genomic Foundation Models via Outlier Removal

Paper • 2505.00598 • Published May 1, 2025 • 1

GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

Paper • 2505.10983 • Published May 16, 2025 • 2

authored a paper over 1 year ago

ESPN: Memory-Efficient Multi-Vector Information Retrieval

Paper • 2312.05417 • Published Dec 9, 2023

authored 3 papers over 1 year ago

GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length

Paper • 2310.00576 • Published Oct 1, 2023 • 2

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Paper • 2401.01325 • Published Jan 2, 2024 • 27

Large Language Models As Faithful Explainers

Paper • 2402.04678 • Published Feb 7, 2024