Search Results for author:
Found 10 papers, 9 papers with code
Autonomous Evaluation and Refinement of Digital Agents
We show that domain-general automatic evaluators can significantly improve the performance of agents for web navigation and device control.
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
In this paper, we develop a framework for building multi-turn RL algorithms for fine-tuning LLMs, that preserves the flexibility of existing single-turn RL methods for LLMs (e. g., proximal policy optimization), while accommodating multiple turns, long horizons, and delayed rewards effectively.
Inversion-Free Image Editing with Natural Language
We show that when the initial sample is known, a special variance schedule reduces the denoising step to the same form as the multi-step consistency sampling.
Ranked #1 on
Text-based Image Editing
on PIE-Bench
SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM
Our results show that, with SmoothQuant+, the Code Llama-34B model can be quantized and deployed on a A100 40GB GPU, achieving lossless accuracy and a throughput increase of 1. 9 to 4. 0 times compared to the FP16 model deployed on two A100 40GB GPUs.
Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?
Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world.
World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models
The ability to connect language units to their referents in the physical world, referred to as grounding, is crucial to learning and understanding grounded meanings of words.
Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification
We evaluate our approach on three existing LTL/natural language datasets and show that we can translate natural language commands at 75\% accuracy with far less human data ($\le$12 annotations).
DANLI: Deliberative Agent for Following Natural Language Instructions
These reactive agents are insufficient for long-horizon complex tasks.
FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing
While edge deletion is a common method used to promote fairness in GNNs, it fails to consider when data is inherently missing fair connections.
Multi-domain Integrative Swin Transformer network for Sparse-View Tomographic Reconstruction
To improve image quality from sparse-view data, a Multi-domain Integrative Swin Transformer network (MIST-net) was developed in this article.
