University of Texas at Austin

university

Verified

https://www.utexas.edu

AI & ML interests

None defined yet.

Recent Activity

reshmijspatel updated a dataset about 20 hours ago

UTEXAS/glioma-cell-chemo

reshmijspatel published a dataset about 20 hours ago

UTEXAS/glioma-cell-chemo

reshmijspatel updated a dataset 1 day ago

UTEXAS/glioma-cell-radiation

View all activity

Papers

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning

Training-free Latent Inter-Frame Pruning with Attention Recovery

View all Papers

updated a dataset about 20 hours ago

UTEXAS/glioma-cell-chemo

Viewer • Updated about 20 hours ago • 15.2k • 11

published a dataset about 20 hours ago

UTEXAS/glioma-cell-chemo

Viewer • Updated about 20 hours ago • 15.2k • 11

updated a dataset 1 day ago

UTEXAS/glioma-cell-radiation

Preview • Updated about 21 hours ago • 5.29k

published a dataset 22 days ago

UTEXAS/glioma-cell-radiation

Preview • Updated about 21 hours ago • 5.29k

submitted a paper to Daily Papers 3 months ago

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning

Paper • 2603.12529 • Published Mar 13 • 19

authored 2 papers 3 months ago

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

Paper • 2403.12945 • Published Mar 19, 2024

Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI

Paper • 2310.01824 • Published Oct 3, 2023 • 1

submitted a paper to Daily Papers 3 months ago

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

Paper • 2603.11653 • Published Mar 12 • 2

submitted a paper to Daily Papers 4 months ago

EntRGi: Entropy Aware Reward Guidance for Diffusion Language Models

Paper • 2602.05000 • Published Feb 4 • 2

posted an update 5 months ago

Post

1641

Are you familiar with reverse residual connections or looping in language models?

Excited to share my Looped-GPT blog post and codebase 🚀
https://github.com/sanyalsunny111/Looped-GPT

TL;DR: looping during pre-training improves generalization.

Plot shows GPT2 LMs pre-trained with 15.73B OWT tokens

P.S. This is my first post here — I have ~4 followers and zero expectations for reach 😄

3 replies

·

authored a paper 6 months ago

Mitigating Catastrophic Forgetting in Mathematical Reasoning Finetuning through Mixed Training

Paper • 2512.13706 • Published Dec 5, 2025 • 1

abao

authored a paper 10 months ago

Concentration of Measure for Distributions Generated via Diffusion Models

Paper • 2501.07741 • Published Jan 13, 2025

authored a paper over 1 year ago

Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations

Paper • 2410.10792 • Published Oct 14, 2024 • 31

authored 4 papers almost 2 years ago

Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion

Paper • 2312.00852 • Published Dec 1, 2023

Generative Modeling with Optimal Transport Maps

Paper • 2110.02999 • Published Oct 6, 2021

RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control

Paper • 2405.17401 • Published May 27, 2024 • 5

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

Paper • 2307.00619 • Published Jul 2, 2023 • 1

authored a paper almost 2 years ago

Comp4D: LLM-Guided Compositional 4D Scene Generation

Paper • 2403.16993 • Published Mar 25, 2024 • 3

authored a paper about 2 years ago

Pre-training Small Base LMs with Fewer Tokens

Paper • 2404.08634 • Published Apr 12, 2024 • 36

ghl

authored a paper over 2 years ago

TIPS: Topologically Important Path Sampling for Anytime Neural Networks

Paper • 2305.08021 • Published May 13, 2023