Joined June 2023
- Tweets61
- Following400
- Followers297
- Likes460
Pinned Tweet
In San Diego for #ACL2026! ☀️
Happy to chat about LLM memory and agents.
Our oral talk: "When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors". LLMs make careless reading mistakes just like humans do.
Mon 7/6, Oral Session D
arxiv.org/abs/2606.32029
Yuqing Yang @ COLM 2026 retweeted
We find that gradients are useful for detecting implicit reward hacking that CoT monitoring can miss.
#COLM2026 poster (Thursday afternoon, Imperial 19)
LLMs can hide reward hacking behind convincing CoTs, making it difficult to detect these behaviors by reading CoT alone. This concern becomes even more pressing for latent or looped LMs.
Our method, Gradient Fingerprint (GRIFT), computes gradients of a model's CoT and compresses them into compact representations. These gradient fingerprints help separate hacking from non-hacking trajectories.
We also show using GRIFT to filter reasoning traces for rejection fine-tuning can suppress reward hacking.
At #COLM2026 now! Come find me at Poster #8 now, where I'm presenting our interpretability work on LLM retraction.
Also would love to swap thoughts on self-improvement, making AI better collaborators, and what academia can still do these days 👋
Yuqing Yang @ COLM 2026 retweeted
I’ll be at the Bay Area for @COLM_conf next week! I’m on the job market this year and I’ll be presenting 3 posters on:
1️⃣ How different models learn similar number representations. convergent-evolution.github.…
2️⃣ Token-level off-policy learning. arxiv.org/abs/2607.17524
3️⃣ SAEs for Reasoning. arxiv.org/abs/2506.09967
Yuqing Yang @ COLM 2026 retweeted
Introducing VaSE: Value-Aware Stochastic KV Cache Eviction.
Reasoning models think in CoT, bloating the KV cache. Eviction caps memory but suffers capability drop. VaSE is a training-free recipe that cuts that cost: keep large-magnitude value states, evict stochastically.
Yuqing Yang @ COLM 2026 retweeted
Excited to share that I’ve started @GoogleResearch as a student researcher today. I'll be working on tabular foundation models. Come and chat if you are around at Google or at the Bay Area.
Excited to share that I've started my summer internship at SystemsResearch@Google in Sunnyvale, working on agentic environment generation!
Always happy to chat about coding agents or LLM memory too. If you're around the Bay Area, would love to meet up.
Yuqing Yang @ COLM 2026 retweeted
The future risk of computer-use agents won’t come only from malicious prompts. It will come from agents that can flawlessly follow normal instructions straight into harm.
Introducing 𝐎𝐒-𝐁𝐥𝐢𝐧𝐝: a realistic but overlooked setting where every task begins with a benign user instruction, yet the harmfulness only emerges as the agent acts in the environment.
Yuqing Yang @ COLM 2026 retweeted
New paper: Convergent Evolution: How Different Language Models Learn Similar Number Representations.
Language models, classical word embeddings, and even raw token frequencies all develop the same Fourier features for numbers. But only some develop the underlying structure. 🧵
Yuqing Yang @ COLM 2026 retweeted
After three papers on Fourier features in LLMs, I think there's a principle worth naming. How should we do science on an LLM?
It corresponds to the existential questions:
> who am I? ↔ the phenomenon.
> where do I come from? ↔ the emergence.
> where am I going? ↔ the use.
🧵
🧵 1/8
What should an LLM assistant remember across conversations?
Existing memory work studies this one task at a time. But real-world assistants see all kinds of conversations, and that changes the problem.
Introducing BEHEMOTH 🦣 + CluE 🌱: a benchmark & self-evolving method for heterogeneous memory extraction.
📄 Paper: arxiv.org/abs/2604.11610
7/8 Bonus findings:
• CluE preserves strengths when starting from a stronger seed
• Transfers to Gemini-3-Flash backend
• Single-step gains carry over to continual memory settings
• Produces clean, structured taxonomies, not bloated rule lists
8/8 Both artifacts may find use beyond this paper.
🦣 BEHEMOTH as a testbed for diverse memory extraction approaches (self-evolving, routing-based, skill-based, and beyond).
🌱 CluE for any setting where one agent must handle heterogeneous demands, e.g. serving users with distinct habits.
w/ @TengxiaoLiu, @BillJohn1235813, @taiwei_shi, @linxins2, @robinomial
Check out the paper & code if this resonates!
Yuqing Yang @ COLM 2026 retweeted
Frontier LLMs don't debug, they regenerate.
We built PDB to measure that gap, GPT-5.1-Codex pass unit tests >76% of the time, but touch only <45% of the right lines.
Even Claude Code touches only ~50%.
📄 Paper: arxiv.org/abs/2604.17338
🌐 Project: precise-debugging-benchmark.…
