activity
20142025
most citedInstruction Tuning with GPT-4

189 citations · 716 across the 29 of their papers we have counts for

collaborators

29 papers

cs.CL2025

Dyna-Mind: Learning to Simulate from Experience for Better AI Agents

Xiao Yu, Baolin Peng, Michel Galley +6

Reasoning models have recently shown remarkable progress in domains such as math and coding. However, their expert-level abilities in math and coding contrast sharply with their pe…

cs.CL2025

SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?

Yao Dou, Michel Galley, Baolin Peng +6

Large language models (LLMs) are increasingly used in interactive applications, and human evaluation remains the gold standard for assessing their performance in multi-turn convers…

cs.CL2025

EfficientLLM: Efficiency in Large Language Models

Zhengqing Yuan, Weixiang Sun, Yixin Liu +13

Large Language Models (LLMs) have driven significant progress, yet their growing parameter counts and context windows incur prohibitive compute, energy, and monetary costs. We intr…

cs.AI2024

Compositional Generalization Across Distributional Shifts with Sparse Tree Operations

Paul Soulos, Henry Conklin, Mattia Opper +3

Neural networks continue to struggle with compositional generalization, and this issue is exacerbated by a lack of massive pre-training. One successful approach for developing neur…

cs.LG2024

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

Tong Chen, Hao Fang, Patrick Xia +5

Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. Howev…

cs.CV2024

Pix2Gif: Motion-Guided Diffusion for GIF Generation

Hitesh Kandala, Jianfeng Gao, Jianwei Yang

We present Pix2Gif, a motion-guided diffusion model for image-to-GIF (video) generation. We tackle this problem differently by formulating the task as an image translation problem…