16 citations · 44 across the 36 of their papers we have counts for
39 papers
KernelSight-LM: A Kernel-Level LLM Inference Simulator
Xiteng Yao, Taeho Kim, Hengzhi Pei +7
As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to m…
Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization
Jiading Gai, Shuai Zhang, Kaj Bostrom +6
We present KernelPro, a closed-loop multi-agent system that automatically generates, profiles, and iteratively optimizes GPU kernel code by integrating large language model (LLM) c…
LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents
Haoyang Fang, Wei Zhu, Boran Han +11
RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity parameters accumulate monotonically across stages, while regularization paramet…
DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts
Jiading Gai, Shuai Zhang, Xiang Song +2
Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared prompt of P tokens, but standard FlashAttention replicates all…
Scalable Prompt Routing via Fine-Grained Latent Task Discovery
Yunyi Zhang, Soji Adeshina, Sheng Guan +5
Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools s…
OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
Haoyang Fang, Shuai Zhang, Yifei Ma +5
Domain-specific finetuning is essential for dense retrievers, yet not all data pairs contribute equally to the learning process. We introduce OPERA, a data pruning framework that e…
XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference
Daniil Vankov, Nikita Ivkin, Kyle Ulrich +3
Mixture-of-Experts (MoE) architectures are increasingly used to efficiently scale large language models. However, in production inference, request batching and speculative decoding…
When LLMs get significantly worse: A statistical approach to detect model degradations
Jonas Kübler, Kailash Budhathoki, Matthäus Kleindessner +4
Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoretically lossless methods and others with…
P-EAGLE: Parallel-Drafting EAGLE with Scalable Training
Mude Hui, Xin Huang, Jaime Campos Salas +5
Reasoning LLMs produce longer outputs, requiring speculative decoding drafters trained on extended sequences. Parallel drafting - predicting multiple tokens per forward pass - offe…
MaxCode: A Max-Reward Reinforcement Learning Framework for Automated Code Optimization
Jiefu Ou, Sapana Chaudhary, Kaj Bostrom +4
Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized…
Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models
Xiyuan Zhang, Danielle C. Maddix, Junming Yin +11
Since the seminal work of TabPFN, research on tabular foundation models (TFMs) based on in-context learning (ICL) has challenged long-standing paradigms in machine learning. Withou…
Chronos-2: From Univariate to Universal Forecasting
Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken +20
Pretrained time series models have enabled inference-only forecasting systems that produce accurate predictions without task-specific training. However, existing approaches largely…
All that structure matches does not glitter
Maya M. Martirossyan, Thomas Egg, Philipp Hoellmer +7
Generative models for materials, especially inorganic crystals, hold potential to transform the theoretical prediction of novel compounds and structures. Advancement in this field…
BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering
Costas Mavromatis, Soji Adeshina, Vassilis N. Ioannidis +6
Knowledge graph question answering (KGQA) presents significant challenges due to the structural and semantic variations across input graphs. Existing works rely on Large Language M…
Beyond instruction-conditioning, MoTE: Mixture of Task Experts for Multi-task Embedding Models
Miguel Romero, Shuoyang Ding, Corey D. Barret +2
Dense embeddings are fundamental to modern machine learning systems, powering Retrieval-Augmented Generation (RAG), information retrieval, and representation learning. While instru…
When Does Multimodality Lead to Better Time Series Forecasting?
Xiyuan Zhang, Boran Han, Haoyang Fang +11
Recently, there has been growing interest in incorporating textual information into foundation models for time series forecasting. However, it remains unclear whether and under wha…
MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
Haoyang Fang, Boran Han, Nick Erickson +10
Existing AutoML systems have advanced the automation of machine learning (ML); however, they still require substantial manual configuration and expert input, particularly when hand…
PropMolFlow: Property-Guided Molecule Generation with Geometry-Complete Flow Matching
Cheng Zeng, Jirui Jin, Connor Ambrose +7
Molecule generation is advancing rapidly in chemical discovery and drug design. Flow matching methods have recently set the state of the art (SOTA) in unconditional molecule genera…
From Demonstrations to Rewards: Alignment Without Explicit Human Preferences
Siliang Zeng, Yao Liu, Huzefa Rangwala +3
One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods,…
Understanding Silent Data Corruption in LLM Training
Jeffrey Ma, Hengzhi Pei, Leonard Lausen +1
As the scale of training large language models (LLMs) increases, one emergent failure is silent data corruption (SDC), where hardware produces incorrect computations without explic…
Open Materials Generation with Stochastic Interpolants
Philipp Hoellmer, Thomas Egg, Maya M. Martirossyan +11
The discovery of new materials is essential for enabling technological advancements. Computational approaches for predicting novel materials must effectively learn the manifold of…
CoddLLM: Empowering Large Language Models for Data Analytics
Jiani Zhang, Hengrui Zhang, Rishav Chakravarti +6
Large Language Models (LLMs) have the potential to revolutionize data analytics by simplifying tasks such as data discovery and SQL query synthesis through natural language interac…
ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs
Hongyi Liu, Rajarshi Saha, Zhen Jia +5
Large Language Models (LLMs) have demonstrated exceptional performance in natural language processing tasks, yet their massive size makes serving them inefficient and costly. Semi-…
A Proximal Operator for Inducing 2:4-Sparsity
Jonas M Kübler, Yu-Xiang Wang, Shoham Sabach +5
Recent hardware advancements in AI Accelerators and GPUs allow to efficiently compute sparse matrix multiplications, especially when 2 out of 4 consecutive weights are set to zero.…