32 citations · 112 across the 94 of their papers we have counts for
14 papers · 1 filter
Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use
Zixiang Chen, Wenting Zhao, Zhepeng Cen +9
Multi-turn tool-use failures can hinge on a single model call, yet reward variation alone does not reveal which call would benefit from training. When rewards depend on later inter…
RAPTOR: Role-Aware Private Training for Mixture-of-Experts
Duc Dm, Khai Le-Duc, Nguyen Do +18
Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see all data while experts only se…
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Cheng Qian, Wenting Zhao, Liangwei Yang +6
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, a…
Moirai 2.0: When Less Is More for Time Series Forecasting
Chenghao Liu, Taha Aksu, Juncheng Liu +7
We introduce Moirai 2.0, a decoder-only time-series foundation model trained on a new corpus of 36M series. The model adopts quantile forecasting and multi-token prediction, improv…
Test-Time Adaptation for LLM Agents via Environment Interaction
Arthur Chen, Zuxin Liu, Jianguo Zhang +6
Large language model (LLM)-based agents struggle to generalize to novel and complex environments, such as unseen websites or new sets of functions, due to a fundamental mismatch be…
xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
Cheng Qian, Zuxin Liu, Shirley Kokane +10
Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle…
CoDA: Coding LM via Diffusion Adaptation
Haolin Chen, Shiyu Wang, Can Qin +12
Diffusion language models promise bidirectional context and infilling capabilities that autoregressive coders lack, yet practical systems remain heavyweight. We introduce CoDA, a 1…
Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models
Xu Liu, Taha Aksu, Juncheng Liu +7
Time series analysis is crucial for understanding dynamics of complex systems. Recent advances in foundation models have led to task-agnostic Time Series Foundation Models (TSFMs)…
GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
Taha Aksu, Gerald Woo, Juncheng Liu +5
Time series foundation models excel in zero-shot forecasting, handling diverse tasks without explicit training. However, the advancement of these models has been hindered by the la…
Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
Xu Liu, Juncheng Liu, Gerald Woo +7
Time series foundation models have demonstrated impressive performance as zero-shot forecasters. However, achieving effectively unified training on time series remains an open chal…
Enabling High Data Throughput Reinforcement Learning on GPUs: A Domain Agnostic Framework for Data-Driven Scientific Research
Tian Lan, Huan Wang, Caiming Xiong +1
We introduce WarpSci, a domain agnostic framework designed to overcome crucial system bottlenecks encountered in the application of reinforcement learning to intricate environments…
Unified Training of Universal Time Series Forecasting Transformers
Gerald Woo, Chenghao Liu, Akshat Kumar +3
Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large…
Causal Layering via Conditional Entropy
Itai Feigenbaum, Devansh Arpit, Huan Wang +5
Causal discovery aims to recover information about an unobserved causal graph from the observable data it generates. Layerings are orderings of the variables which place causes bef…
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
Tianyu Guo, Wei Hu, Song Mei +4
While large language models based on the transformer architecture have demonstrated remarkable in-context learning (ICL) capabilities, understandings of such capabilities are still…