Computer Science at UT Austin

UTCS is a recognized leader in creating the scientific knowledge and practical technologies exemplifying the digital revolution that defines the 21st century.

[Computer Science at UT Austin @UTCompSci]

@UTAustin is launching a new School of Computing in fall 2026! With Information and Statistics & Data Science, we’ll expand student opportunities, accelerate research, and strengthen pathways to high-impact careers and grad study.

Read more: https://t.co/Kjg3k1gZKZ

[The University of Texas System @utsystem]

The future of robotics is being tested one kick at a time. A @utaustin robot soccer team,  is heading to South Korea for the RoboCup — where they will compete against other teams while also advancing research in AI, perception, and teamwork. By teaching robot complex skills like dribbling and passing, researchers are helping develop systems that can learn, adapt, and solve real-world challenges. @UTCompSci has more: https://t.co/z0vpU04Xmi

[Yue Zhang @zhan1624]

AI video looks incredible until something moves.

Paper towels dissolve instead of soaking up water. Balls bounce off pillows like they're on a trampoline. Gravity stops being a law and starts being a suggestion.

Physics is the thing AI video still struggles with. We introduce our #ECCV2026 paper --- Physics Question Scene Graph (PQSG), a fine-grained evaluation framework for measuring physical plausibility in text-to-video generation.

– Diagnose, not just score
Identify exactly which objects, actions, and physical interactions fail in generated videos.

– Dependency-aware evaluation
Evaluate physics only when prerequisite objects and actions are correctly generated.

– Human-aligned physical realism
Achieve a stronger correlation with human judgments than existing video evaluation metrics.

[Mohit Bansal @mohitban47]

👋 Looking forward to attending #ACL2026 (in-person in San Diego) and #ICML2026 (probably virtually) for these presentations/workshop keynotes & meeting everyone (also, I'll be in the Bay Area beforehand, for a keynote at the Apple Reasoning and Planning Workshop)!

Feel free to ping if you want to meet up in Bay/SD (I also have July1 partly free in SJ/SF, and several days in SD), and discuss research, life, etc. (we're also hiring at all levels: phd, postdoc, faculty)! 🙂

PS. also meet several of our awesome students/postdocs/alumni attending these 2 conferences to present these works.
👇👇

[Matt Lease @mattlease]

Alignment study @aclmeeting #acl2026 by @gkambhat w/ @jessyjli @Sanjana08395511, Angela Zhang, Alex Liu, & Ravi Srinivasan. Paper https://t.co/CKm8hZdwN4, Slides https://t.co/hJqjyjFIa6, video https://t.co/nG9zwOzbh4. @UTGoodSystems @CosmicAI_Inst @UTiSchool @UTCompSci #TexasAI

[Michelle Lam @michelle123lam]

After over 10 years at Stanford, it's time to leave :)

I will be joining UT Austin's CS department as an assistant professor in fall 2027! If you're excited to envision the future of interaction with AI, I'm recruiting PhD students this cycle. Come join me!

[Qixing Huang @ICERM @qixing_huang]

Very happy that a paper originated from a course project last Fall was accepted by ECCV 2026. It is about consistent spherical parametrizations via a generative model. joint work with Sai Karthikey Pentapati, Shashank Gupta, Rajesh Sureddi, Yuezhi Yang, and Alan Bovik

[Elias Stengel-Eskin @EliasEskin]

🚨 Excited to share Pragmatic Reasoning via Self-Training, a method for LLM self-improvent on pragmatic reasoning. PragReST improves by +5.37% and +5.50% for Qwen3-8B/14B across pragmatics benchmarks with no human annotations or teacher models.

LLMs still struggle w/ pragmatics: understanding what a speaker means, not just what they literally said. They often default to literal interpretations and miss implicature, intent, or context-dependent meaning. To close this gap, we started with a key question: Can we treat pragmatics as a LLM reasoning task?

➡️ Following a long line of work in pragmatics (e.g. RSA, IBR), PragReST treats pragmatic understanding as counterfactual reasoning. Instead of teaching models to ask “is this interpretation compatible with the words?”, we teach the model to reason about questions like “if the speaker meant something else, what would they have said instead?”

➡️ PragReST is self-improving: it self-generates pragmatic QA data, self-filters noisy examples, learns counterfactual reasoning traces via SFT, and further improves with GRPO using a self-judged correctness reward.

➡️ Error analysis shows that gains correlate with increased counterfactual reasoning. This suggests PragReST’s improvements are tied to reasoning over communicative alternatives, rather than simply more pragmatic data or more training.

🧵👇

[Computer Science at UT Austin @UTCompSci]

@michelle123lam Welcome you to UTCS!! 🤘🎉

[Computer Science at UT Austin @UTCompSci]

We are deeply saddened by the loss of Joshua Baer, a longtime mentor and advocate for student entrepreneurship. For over a decade, Josh led the Longhorn Startup program, inspiring students to pursue bold ideas and create lasting impact. We extend our heartfelt condolences.

[Isil Dillig @IsilDillig]

1/7
If you’re at #PLDI2026 in Boulder this week, come see what our group has been up to! We’re presenting work on making code generation more interactive and reliable, speeding up data pipelines, porting network data-plane programs,

[UT Austin @UTAustin]

What happens when experts in artificial intelligence, robotics, engineering and cancer care come together to tackle some of medicine's biggest challenges?

Researchers from UT Austin, @DellMedSchool and @UTMDAnderson Cancer Center are joining forces through the Collaborative Accelerator for Transformative Research Endeavors.

More than 50 researchers are working across disciplines to advance personalized robotic-assisted surgery, AI-powered precision medicine and new approaches to cancer care and treatment.

Learn more: https://t.co/JJMwRHW7mC

[Elias Stengel-Eskin @EliasEskin]

🚨 Test-time intervention for CUA tasks is hard: history is hard to represent, actions require visual grounding and verification before execution, not after. HiViG jointly tackles these points, learning to track history and verify actions against the GUI screenshot.

As a test-time method, HiViG is compatible w/ open- and closed-source models and is domain- and model-general: we see 5.8-9% accuracy gains across WebArenaLite2 (web), AndroidLab (mobile) and WindowsAgentArena (desktop), and across models/model classes (e.g., Qwen3-VL-32B, Gemini-3-Flash), with especially large gains on challenging/long-horizon tasks (+19.2% on WebArenaLiteV2 Maps, +18.6% on WindowsAgentArena Office).

🧵👇

[Computer Science at UT Austin @UTCompSci]

@_yudaitanaka Welcome to UTCS, Professor Yudai! 🤘🎉

[Yudai Tanaka @_yudaitanaka]

I’m thrilled to share that I’ll be joining UT Austin Computer Science (@UTCompSci ) as an Assistant Professor, starting Jan 2027!

I'm recruiting PhD students for Fall 2027, postdocs, and researchers at all levels:
https://t.co/nuFzfF2ErP

I’ll continue my work (https://t.co/kslxLafmya) in Human-Computer Interaction (HCI) and start the Symbiotic Interfaces Lab, where we’ll explore how computational systems & humans can co-adapt to augment human sensorimotor and cognitive abilities. 🦾🧠

[Priyanka Mandikal @PrnkMandikal]

🤖 How can robots learn long-horizon object state change tasks like mashing a banana 🥣🍌, spreading ketchup on bread 🍅🍞, or slicing a cucumber 🔪🥒?

Introducing SPARTA: object state-change manipulation via visual spatial progress 👇

🌐 https://t.co/pzRiSYqHjc

[Zaid Khan @codezakh]

Can an LLM act as a selective model of a GPU during evolutionary search, by reasoning + forecasting a kernel’s runtime but deferring to a GPU when unsure? We produced 12k kernels + runtimes from evolutionary search, costing 400M reasoning tokens + 600 GPU-hours to answer this.

In our work GPU Forecasters, we study language models as selective surrogates for GPU kernel optimization.

1️⃣ Off-the-shelf LLMs can forecast how a GPU responds to a candidate kernel with non-trivial accuracy. If we rank candidates by these predictions and measure only the top 10% on a GPU, the fastest kernel we find is within 20% of the best in the pool.

2️⃣ We want LLMs to not just be accurate but also calibrated, so that we can use their uncertainty for selective prediction: during search, we should trust only confident forecasts and verify less confident forecasts by sending them to the GPU.

3️⃣ We train an open-weights surrogate (GPT-OSS-20B) with RL to improve both accuracy and calibration. Calibration-shaped rewards improve both confidence reliability and ranking ability, while correctness rewards alone do not.

4️⃣ Inside a real kernel search, the surrogate finds faster kernels than an equal-GPU-budget baseline by considering more candidates per measurement.

5️⃣ We release 12,388 LLM-generated GPU kernels with measured runtimes spanning 118 operations, CUDA and Triton backends, 3 GPU types, taking 400M tokens + 600 GPU-hours to produce. This dataset can be used for analyzing LLM-driven evolutionary program search dynamics, post-training LLMs for kernel code generation, and things we didn’t get a chance to explore, like training reward models!

Thread 🧵👇

[Yuke Zhu @yukez]

Exciting news on GR00T:

NVIDIA announces our first open humanoid robot platform, featuring Unitree H2 Plus and Sharpa hands, to accelerate academic research and facilitate cross-institutional collaboration.

R&D in humanoid robotics needs broader participation. Open science is how we build the future faster, together.

[Swarat Chaudhuri @swarat]

Delighted to finally unveil these results! 🎉

Many congratulations to the team, who worked tirelessly for almost a year to build and evaluate AlphaProof Nexus. We revised many priors during this project — most notably, we discovered that with current frontier models, simple agent loops with compiler feedback can rival more sophisticated systems. We were struck both by the capabilities of our systems and the magnitude of the challenges ahead.

I have never been as excited about the potential of formal math to enhance human creativity and bring rigor to AI. Onward! 🚀

[Chenfeng_X @Chenfeng_X]

Excited that our paper StreamdiffusionV2 received the Best Research Paper Award at #MLSys26!

🚀Video generation is quickly moving from demos to production-facing workloads. It is no longer a turn-based pipeline but should be a streaming pipeline to interact with users.

📖Our project page: https://t.co/ItuO5zc6hT and paper: https://t.co/fmz2irYIm1

👂Come join the talk if you are interested in streaming video generation. Our talk will be at the Research Track Oral Presentation: Best Paper Session on Tue 8:45AM at #MLSys26 , I will talk about how we attacked the efficiency and quality challenges. Hope to see you there!

❤️Huge thanks to all authors! This work would not have been possible without the incredible effort from the entire team. Big shout out to Tianrui Feng, Zhi Li, @Andy_ShuoYang , @HaochengXiUCB, @lmxyy1999 , @lvminzhang , @xiuyu_l , Keting Yang, @ZiqiPeng, @songhan_mit , @magrawala, @KurtKeutzer , and @cumulo_autumn

[Joydeep Biswas @Joydeepb_robots]

Are state-of-the-art AI review systems capable of providing meaningful reviews in an actual AI conference? This paper explains the findings from the AAAI 2026 AI Review Pilot 1/N