1.5k citations · 3.6k across the 48 of their papers we have counts for
49 papers
PathFM: Fast Generative Forecasting of Multivariate Trajectories
Jiachen Yao, Xiyuan Zhang, Annan Yu +5
Time series foundation models are becoming increasingly popular for general-purpose forecasting. However, most leading models predict marginal quantiles, leaving the dependence str…
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…
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…
SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning
Zelin He, Boran Han, Xiyuan Zhang +10
Time-series diagnostic reasoning is essential for many applications, yet existing solutions face a persistent gap: general reasoning large language models (GRLMs) possess strong re…
Efficient Table Retrieval and Understanding with Multimodal Large Language Models
Zhuoyan Xu, Haoyang Fang, Boran Han +4
Tabular data is frequently captured in image form across a wide range of real-world scenarios such as financial reports, handwritten records, and document scans. These visual repre…
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…
HetRL: Efficient Reinforcement Learning for LLMs in Heterogeneous Environments
Yongjun He, Shuai Zhang, Jiading Gai +5
As large language models (LLMs) continue to scale and new GPUs are released even more frequently, there is an increasing demand for LLM post-training in heterogeneous environments…
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…
Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices
Yilong Li, Shuai Zhang, Yijing Zeng +5
Large Multimodal Models (LMMs) are inherently modular, comprising vision and audio encoders, a projector, and a language backbone. Yet existing systems execute them monolithically,…
CrEst: Credibility Estimation for Contexts in LLMs via Weak Supervision
Dyah Adila, Shuai Zhang, Boran Han +2
The integration of contextual information has significantly enhanced the performance of large language models (LLMs) on knowledge-intensive tasks. However, existing methods often o…
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…
Visual Instruction Tuning with Chain of Region-of-Interest
Yixin Chen, Shuai Zhang, Boran Han +1
High-resolution (HR) images are pivotal for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs). However, directly increasing image…
A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms
Chengkai Huang, Hongtao Huang, Tong Yu +6
Recommender systems (RS) have become essential in filtering information and personalizing content for users. RS techniques have traditionally relied on modeling interactions betwee…
Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach
Dheeraj Baby, Boran Han, Shuai Zhang +3
We study the well-motivated problem of online distribution shift in which the data arrive in batches and the distribution of each batch can change arbitrarily over time. Since the…
Toward Holistic Evaluation of Recommender Systems Powered by Generative Models
Yashar Deldjoo, Nikhil Mehta, Maheswaran Sathiamoorthy +3
Recommender systems powered by generative models (Gen-RecSys) extend beyond classical item ranking by producing open-ended content, which simultaneously unlocks richer user experie…
Effectively Steer LLM To Follow Preference via Building Confident Directions
Bingqing Song, Boran Han, Shuai Zhang +5
Having an LLM that aligns with human preferences is essential for accommodating individual needs, such as maintaining writing style or generating specific topics of interest. The m…
Multimodal Instruction Tuning with Hybrid State Space Models
Jianing Zhou, Han Li, Shuai Zhang +5
Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high…
Unraveling the Gradient Descent Dynamics of Transformers
Bingqing Song, Boran Han, Shuai Zhang +2
While the Transformer architecture has achieved remarkable success across various domains, a thorough theoretical foundation explaining its optimization dynamics is yet to be fully…
PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
Yilong Li, Jingyu Liu, Hao Zhang +7
Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy c…
Transferring Knowledge from Large Foundation Models to Small Downstream Models
Shikai Qiu, Boran Han, Danielle C. Maddix +3
How do we transfer the relevant knowledge from ever larger foundation models into small, task-specific downstream models that can run at much lower costs? Standard transfer learnin…
Discovering Bias in Latent Space: An Unsupervised Debiasing Approach
Dyah Adila, Shuai Zhang, Boran Han +1
The question-answering (QA) capabilities of foundation models are highly sensitive to prompt variations, rendering their performance susceptible to superficial, non-meaning-alterin…
CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving
Pei Chen, Boran Han, Shuai Zhang
Large Language Models (LLMs) have shown great ability in solving traditional natural language tasks and elementary reasoning tasks with appropriate prompting techniques. However, t…