117 citations · 704 across the 174 of their papers we have counts for
26 papers · 1 filter
On the Accuracy of Approximate Leave-One-Out with Blockwise Nonsmooth Regularization in High-dimensions
Honghao Lin, Songbin Liu, Arian Maleki +5
Approximate leave-one-out (ALO) refers to methods that provide computationally efficient and statistically accurate approximations to leave-one-out risk estimation. These methods h…
DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck
Shubham Agarwal, Akshat Gupta, Mike Heddes +21
Evaluation has been central to advances in AI, and it is equally critical to autonomous discovery. Yet scaling autonomous discovery to real-world engineering challenges faces a fun…
Optimal and Efficient Online Inverse Optimization
Anupam Gupta, Guru Guruganesh, Honghao Lin +3
In online inverse linear optimization, a learner recommends an action and then observes the choice of an expert who maximizes a fixed, unknown linear objective on ;…
BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding Models
Gang Fu, Adel Javanmard, MohammadHossein Bateni +1
Mixture-of-experts (MoE) layers increase model capacity without a proportional increase in per-example computation. However, conventional flat routers can yield imbalanced expert u…
A Proof of the Most Informative Boolean Function Conjecture
Zijie Chen, Amin Gohari, Adel Javanmard +4
Let be uniform on , let be obtained by passing its coordinates independently through a binary symmetric channel with crossover probability , and let $g:\{-1,…
DLB: Distributed Load Balancing at Scale for Generative AI Inference
Santiago R. Balseiro, Bartek Wydrowski, Sameer Agarwal +11
The reliance on scarce and expensive accelerators such as GPUs and TPUs in modern datacenters places unprecedented demands on backend infrastructure. For workloads characterized by…
Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science
Honghao Lin, David P. Woodruff, Yuan Deng +3
Language models can produce plausible short proofs, but may still be unreliable on long-horizon research problems, where progress depends on a sequence of uncertain and interdepend…
TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability
Vincent Cohen-Addad, Dimitris Paparas, Ernest van Wijland +13
We introduce TCS-Bench, a benchmark for evaluating Large Language Models (LLMs) on research-level Theoretical Computer Science (TCS) proof generation. TCS-Bench consists of theorem…
Nearly Optimal Strong Coresets for Subspace Approximation
Honghao Lin, Vahab Mirrokni, David P. Woodruff
We study strong coresets for subspace approximation. Given a matrix , the goal is to sample and rescale a small number of its rows to obtain $S…
Proteus: Incremental Memory Activation for Long-Context Sequence Modeling
Reza Bayat, Ali Behrouz, Vahab Mirrokni +1
The quadratic cost of attention-based sequence models for long contexts has motivated a growing line of research on memory-based models that can compress context into a compact sta…
SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant
Adel Javanmard, David P. Woodruff, Vahab Mirrokni
Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging. Existing vector quantization methods, such as vqSGD,…
A Near-Optimal Lower Bound for Prefix-Matrix Factorizations
Honghao Lin, Vahab Mirrokni, David P. Woodruff
For the lower-triangular all-ones matrix , we prove a near-optimal lower bound \[ γ_{2,1}(Q) := \inf_{Q=AB} \|A\|_{2\to\infty}\|B\|_{1\to1} = Ω\!\left( \frac{\log^{3…
Pairwise-Independent Dithering for Single-Stage Hadamard Quantization
Honghao Lin, Vahab Mirrokni, David P. Woodruff
Quantizing high-dimensional vectors is fundamental to similarity search, distributed learning, and model compression. Feng, Indyk, Kapralov, Krachun, and Prokhorov established shar…
The Condition-Number Barrier in Sparse Least Squares
Honghao Lin, Vahab Mirrokni, David P. Woodruff
In [AS21], Axiotis and Sviridenko conjectured that the linear dependence on the restricted condition number in sparse convex optimization cannot be improved by a polynomial-time al…
Near-Optimal Dimension Lower Bounds for Single-Vector Embeddings of Maximum Inner Product Similarity
Rajesh Jayaram, Honghao Lin, Vahab Mirrokni +1
Multi-vector embeddings represent items by point clouds and compare query and document point clouds using Chamfer similarity, whereas single-vector embeddings use ordinary inner pr…
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Ali Behrouz, Farnoosh Hashemi, Adel Javanmard +1
The past few decades have witnessed significant advances in the design of machine learning algorithms, from early studies on task-specific shallow models to more general deep Large…
Quota Marketplace: Dynamic Pricing for Efficient Allocation of ML Training Resources
Balasubramanian Sivan, Renato Paes Leme, Mihai Tiuca +6
The escalating demand for Machine Learning (ML) training resources in recent years has resulted in a substantial gap between the high demand and the available supply. Efficient all…
HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
Dongyeun Lee, Amir Zandieh, Vahab Mirrokni +2
Video Diffusion Transformers (VDiTs) have demonstrated significant capabilities in high-fidelity video generation. However, their ability to produce long-duration videos is fundame…
Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness
Aria Masoomi, Mahsa Bazzaz, Adel Javanmard +1
Chain-of-thought (CoT) reasoning enables large language models (LLMs) to solve complex problems by generating intermediate reasoning steps. While much attention has been paid to th…
Towards Automating Scientific Review with Google's Paper Assistant Tool
Rajesh Jayaram, Drew Tyler, David Woodruff +4
Artificial intelligence is driving a revolution in scientific discovery, accelerating everything from hypothesis generation to mathematical theorem proving. However, this rapid acc…
Active Learning with Low-Rank Structure for Data Selection
Vincent Cohen-Addad, Sasidhar Kunapuli, Vahab Mirrokni +3
In the data selection problem, the objective is to choose a small, representative subset of data that can be used to efficiently train a machine learning model. Sener and Savarese…
Aletheia tackles FirstProof autonomously
Tony Feng, Junehyuk Jung, Sang-hyun Kim +14
We report the performance of Aletheia (Feng et al., 2026b), a mathematics research agent powered by Gemini 3 Deep Think, on the inaugural FirstProof challenge. Within the allowed t…
Accelerating Scientific Research with Gemini: Case Studies and Common Techniques
David P. Woodruff, Vincent Cohen-Addad, Lalit Jain +33
Recent advances in large language models (LLMs) have opened new avenues for accelerating scientific research. While models are increasingly capable of assisting with routine tasks,…
Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
Adel Javanmard, Baharan Mirzasoleiman, Vahab Mirrokni
Large Language Models (LLMs) are pretrained on massive datasets and later instruction-tuned via supervised fine-tuning (SFT) or reinforcement learning (RL). Best practices emphasiz…