Daniel Kang

@ddkang

Distinguished AI research scientist at Bridgewater AIA labs, asst. professor at UIUC CS. Formerly in the Stanford DAWN lab and the Berkeley Sky Lab.

New York, NY

ddkang.github.io

Joined November 2010

103 Following

6,388 Followers

Replies Reposts Media

Daniel Kang
@ddkang
Sep 18
We've long known that AI agent benchmarks are broken. Check out our work back from July 2025 on establishing best practices for making rigorous AI agent benchmarks! (links below)
Epoch AI
@EpochAIResearch
Sep 17
Introducing Benchmark Reviews: our new initiative to audit AI benchmarks. We are launching with 15 benchmarks: 4 Verified, 9 Flawed, and 2 with not enough information for a review.
9
Daniel Kang
@ddkang
Aug 27
New research from Bridgewater AIA Labs and UIUC, in collaboration with Thinking Machines! We use @tinkerapi to achieve state-of-the-art on a cleaned version of the BIRD text-to-SQL dataset, outperforming all frontier models we tested (including Fable and Sol) up to 8x cheaper.
Tinker
@tinkerapi
Aug 27
LLMs with scaffolds have lagged on text-to-SQL, a task that relies on human judgment. By folding expert judgment into every part of RLVR on Tinker, @maxYuxuanZhu and @ddkang (UIUC and Bridgwater) trained the first text-to-SQL model to beat the human mark. thinkingmachines.ai/news/putting-t…
5
Daniel Kang
@ddkang
Aug 3
Prior work has shown a counter-intuitive idea that RLVR boosts reasoning using 100% noisy data to a similar level of using clean data. We show that this is false through a more rigorous process of constructing noisy data. We demonstrate that RLVR with noisy data leads to worse
Stella Li @ COLM
@StellaLisy
May 27, 2025
🤯 We cracked RLVR with... Random Rewards?! Training Qwen2.5-Math-7B with our Spurious Rewards improved MATH-500 by: - Random rewards: +21% - Incorrect rewards: +25% - (FYI) Ground-truth rewards: + 28.8% How could this even work⁉️ Here's why: 🧵 Blogpost: tinyurl.com/spurious-rewar…
14
Daniel Kang
@ddkang
Jul 27
Building text-to-SQL agents? Don’t blindly trust benchmarks/leaderboards. In our VLDB 2026 paper, we find >50% annotation error rates in BIRD and Spider 2.0-Snow, two widely used text-to-SQL benchmarks, shifting agents’ measured performance by up to 19%. 1/9
3
Daniel Kang
@ddkang
Jul 20
New research from Bridgewater AIA Labs, UIUC, and MIT: we prove what we believe to be the first non-vacuous generalization bounds for reasoning LLMs on real-world problems. RLVR powers frontier reasoning capabilities yet its generalization to unseen data has remained an open
2