276 citations · 1.2k across the 50 of their papers we have counts for
14 papers · 1 filter
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
Yiheng Xu, Zekun Wang, Junli Wang +6
Automating GUI tasks remains challenging due to reliance on textual representations, platform-specific action spaces, and limited reasoning capabilities. We introduce Aguvis, a uni…
PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
Yun Peng, Akhilesh Deepak Gotmare, Michael Lyu +3
Large Language Models (LLMs) are widely adopted for assisting in software development tasks, yet their performance evaluations have narrowly focused on the functional correctness o…
CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
Jierui Li, Hung Le, Yingbo Zhou +3
Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional ex…
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…
XForecast: Evaluating Natural Language Explanations for Time Series Forecasting
Taha Aksu, Chenghao Liu, Amrita Saha +3
Time series forecasting aids decision-making, especially for stakeholders who rely on accurate predictions, making it very important to understand and explain these models to ensur…
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…
MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs
Lei Wang, Shan Dong, Yuhui Xu +6
Recent large language models (LLMs) have demonstrated versatile capabilities in long-context scenarios. Although some recent benchmarks have been developed to evaluate the long-con…
Automatic Curriculum Expert Iteration for Reliable LLM Reasoning
Zirui Zhao, Hanze Dong, Amrita Saha +2
Hallucinations (i.e., generating plausible but inaccurate content) and laziness (i.e. excessive refusals or defaulting to "I don't know") persist as major challenges in LLM reasoni…
ThinK: Thinner Key Cache by Query-Driven Pruning
Yuhui Xu, Zhanming Jie, Hanze Dong +6
Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their incr…
INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
Hung Le, Yingbo Zhou, Caiming Xiong +2
Large language models (LLMs) for code are typically trained to align with natural language instructions to closely follow their intentions and requirements. However, in many practi…
UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting
Juncheng Liu, Chenghao Liu, Gerald Woo +4
Transformer-based models have emerged as powerful tools for multivariate time series forecasting (MTSF). However, existing Transformer models often fall short of capturing both int…
RLHF Workflow: From Reward Modeling to Online RLHF
Hanze Dong, Wei Xiong, Bo Pang +7
We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpa…
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…
Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions
David Junhao Zhang, Dongxu Li, Hung Le +3
Most existing video diffusion models (VDMs) are limited to mere text conditions. Thereby, they are usually lacking in control over visual appearance and geometry structure of the g…