Meta FAIR, NYU PhD @agentic_ai_lab • NDSEG fellow • prev Voleon Group, UMich CS
New York, NY
Joined December 2022
- Tweets154
- Following639
- Followers674
- Likes1.2K
Pinned Tweet
Our work Midway Network has been accepted to #ICLR2026!
Animals learn to recognize objects and how they move just from observing the world. SSL on natural videos emulates “learning by observing” but only tackles recognition or motion, not both!
To address this gap, Midway Network is the first SSL architecture to learn both object recognition and motion understanding from natural videos via latent dynamics🧵
Interesting, it seems like the linear probe it learns tries to imitate self-judgment / best-of-N. Curious if it can still improve itself with thinking on?
1/
What if an LLM could not just edit a model's weights, but re-architect it as it trains?
We tried just that. The resulting architectures exit the known territory of transformers: the coding agents spliced code directly into the network.
On nanochat, the loss fell below ordinary training after each new code layer was introduced. On algorithmic reasoning, accuracy rose from 55% to 84%. We even let DeepSeek-V4.1-Flash act as the agent modifying itself, raising its AIME and HMMT 2026 score from 64% to 71%.
To do all this, the agents built a set of tools we’ve never seen before, which we call mechanistic intervention!
Blog: doubleai.s.gy/llm-redesign
154
Chris Hoang retweeted
Happy to release a small report on some studies at Cursor on stabilizing the combination of RL + self-distillation in production-like agentic settings. w/ @srush_nlp and @ashvinair
arxiv.org/abs/2611.05266
This work/setup is a bit stale now, but could provide some insight on what pitfalls to lookout for!
Chris Hoang retweeted
Robots need to feel where they touch and how forces change. Introducing PanoTac: an open-source, dense 3D tactile sensor for <$10 USD.
Watch as the robot racks a test tube and pulls the stopper: PanoTac tells the tube orientation, and feels when the stopper comes free. 🧵
Chris Hoang retweeted
Do you really need a video autoencoder for your video generator?
Meet U-JiT: video generation directly in pixel space, trained end-to-end to achieve state-of-the-art results on Kinetics-600
The key: re-thinking compression through the architecture ⬇️
Chris Hoang retweeted
New paper: Outerloop: Open and Trustworthy Multi-Agent Autoresearch. In most open autoresearch systems, the agent grades its own results. Outerloop is a kernel that runs agents as untrusted programs and keeps measurement and review outside their sandboxes.
Chris Hoang retweeted
Energy-Based Models can now scale better than Diffusion models.
Introducing TEM: Transformer Energy-based Models
TLDR:
• TEM outscales Diffusion without guidance
• First scalable contrastive Energy-Based Models
• Better generalization, test-time scaling, and OOD detection than Diffusion
🧵
Chris Hoang retweeted
Excited to announce that my benchmark, CorporateBench (EMNLP), has been added to the @FireworksAI_HQ Specialized Intelligence Index!
ailabs.epiqglobal.com/announ…
This quoted post is unavailable.
Chris Hoang retweeted
💥 In our newest paper, we find a "Hawthorne effect” for your personal agents in negotiation: they act differently when you are around! 🤯
🙅 With personal agents like Claude Duet and Meta Muse on the rise, understanding how user involvement shapes agent behavior is increasingly important. We uncover a counterintuitive finding: having a user in the loop can actually induce more agent misbehavior❗️
🧵👇
Chris Hoang retweeted
We let agent swarms collaborate for 10K hours in simulated agent-owned GitHubs.
Gemini-3.8-flash collaborate the best while gpt-6-astra scores the worst among frontier models tested⁉️
What are the elements of successful agent collaboration at scale? Check World of SWECraft 🧵
Chris Hoang retweeted
World models can fail when the world changes.
That's why CDS PhD student Ying Wang (@yingwww_), CDS founding director Yann LeCun (@ylecun) & CDS Assistant Professor Mengye Ren (@mengyer) built AdaJEPA to adapt during planning.
nyudatascience.medium.com/a-…
Chris Hoang retweeted
New #NVIDIA paper: what if robots never had to wait for their own thoughts?
TacitVLA learns to reason in chain-of-thought or subtasks, but its actions never read them.
→ Keeps the gains of reasoning at up to 3.4× lower latency on 4 benchmarks, and tops RoboMME and RMBench 🧵👇
Chris Hoang retweeted
Excited to announce that two of my papers on synthetic data gen from our team at Epiq AI Labs were accepted to NeurIPS and EMNLP 2026!
Introducing InvestigationWorlds and CorporateBench... 🧵
Chris Hoang retweeted
🌶️ if your benchmark can be gamed, it will be... so you’d better game it first!
excited to present Benchmark Designers Should "Train on the Test Set” to Expose Exploitable Non-Visual Shortcuts at #COLM2026 today!
📍 Poster #124 · Grand Ballroom @ 4:40pm
Chris Hoang retweeted
What if LLMs could think in weights, not tokens?
Introducing HyperThink (#COLM2026, co-led with @kdgyun425): a hypernetwork writes a per-question weight update to the LLM for it to skip the long thinking trace, a step toward accurate System 1 thinking! 🧵👇
📍 Tomorrow at @COLM_conf! Oct 6 (Tue), 4:30 to 6:30 PM, board #97, Franciscan C
Chris Hoang retweeted
👋 𝗛𝗲𝗹𝗹𝗼 𝗧𝘄𝗶𝘁𝘁𝗲𝗿! 𝗙𝗶𝗿𝘀𝘁 𝘁𝘄𝗲𝗲𝘁 𝗮𝗹𝗲𝗿𝘁 🚨
Why not give it to a paper!
Excited to share our work at @Meta: 𝗣𝗿𝗼𝗪𝗔𝗠
In this paper, we try to answer:
"How should a robot imagine the future before it acts?"
🌐 Webpage: sii-ferenas.github.io/ProWAM…
🧵👇
Chris Hoang retweeted
Honored to receive the 2nd Annual Google ML and Systems Junior Faculty Award for our work on adaptable ML systems and agents. Grateful to @Google for the support, and to my students. More to come on adaptable agents, in open source and open science.
Chris Hoang retweeted
Outerloop 0.1.0 is out. A fleet of AI agents that improve your benchmarks on your code. Agents propose changes, run them on your cluster, and open pull requests when the metrics improve. We are open source. Let's embrace open science! Get started at outerloop.science