University of Texas at Austin

university

Verified

https://www.utexas.edu

AI & ML interests

None defined yet.

Recent Activity

acnagle submitted a paper about 1 month ago

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

jehuhuhuhu authored a paper about 1 month ago

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

jehuhuhuhu authored a paper about 1 month ago

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

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

authored a paper 5 days ago

ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

Paper • 2603.28737 • Published 20 days ago

submitted a paper to Daily Papers about 1 month ago

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

Paper • 2603.12529 • Published Mar 13 • 19

submitted 2 papers to Daily Papers about 1 month ago

Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control

Paper • 2603.09221 • Published Mar 10

nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

Paper • 2603.04948 • Published Mar 5 • 2

MaryamPaparimoghadamborazjani

updated a Space about 2 months ago

Maryam Paparimoghadamborazjani Portfolio

Generate a personalized greeting for visitors

MaryamPaparimoghadamborazjani

published a Space about 2 months ago

Maryam Paparimoghadamborazjani Portfolio

Generate a personalized greeting for visitors

submitted a paper to Daily Papers 2 months ago

EntRGi: Entropy Aware Reward Guidance for Diffusion Language Models

Paper • 2602.05000 • Published Feb 4 • 1

posted an update 3 months ago

Post

1630

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 4 months ago

Cautious Weight Decay

Paper • 2510.12402 • Published Oct 14, 2025 • 10

authored a paper 4 months ago

Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models

Paper • 2512.03125 • Published Dec 2, 2025 • 3

authored a paper 9 months ago

MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding

Paper • 2507.12463 • Published Jul 16, 2025 • 27

authored a paper 10 months ago

LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation

Paper • 2501.05414 • Published Jan 9, 2025 • 2

authored a paper 10 months ago

Rhapsody: A Dataset for Highlight Detection in Podcasts

Paper • 2505.19429 • Published May 26, 2025 • 1

authored a paper 11 months ago

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

Paper • 2505.13444 • Published May 19, 2025 • 16

authored a paper about 1 year ago

Scaling Rich Style-Prompted Text-to-Speech Datasets

Paper • 2503.04713 • Published Mar 6, 2025 • 1

authored a paper about 1 year ago

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

Paper • 2502.06608 • Published Feb 10, 2025 • 39

authored a paper about 1 year ago

PhD Knowledge Not Required: A Reasoning Challenge for Large Language Models

Paper • 2502.01584 • Published Feb 3, 2025 • 9

authored a paper over 1 year ago

Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding

Paper • 2501.00712 • Published Jan 1, 2025 • 6

authored 2 papers over 1 year ago

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

Paper • 2411.05361 • Published Nov 8, 2024 • 5

Textless Speech-to-Speech Translation With Limited Parallel Data

Paper • 2305.15405 • Published May 24, 2023