13 citations · 71 across the 26 of their papers we have counts for
17 papers · 1 filter
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…
GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
Qianhui Wu, Kanzhi Cheng, Rui Yang +15
One of the principal challenges in building VLM-powered GUI agents is visual grounding, i.e., localizing the appropriate screen region for action execution based on both the visual…
On Memory Construction and Retrieval for Personalized Conversational Agents
Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang +8
To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory ba…
SCBench: A KV Cache-Centric Analysis of Long-Context Methods
Yucheng Li, Huiqiang Jiang, Qianhui Wu +8
Long-context LLMs have enabled numerous downstream applications but also introduced significant challenges related to computational and memory efficiency. To address these challeng…
TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning
Shivam Shandilya, Menglin Xia, Supriyo Ghosh +4
The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading…
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Huiqiang Jiang, Yucheng Li, Chengruidong Zhang +9
The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase.…
Mitigate Position Bias in Large Language Models via Scaling a Single Dimension
Yijiong Yu, Huiqiang Jiang, Xufang Luo +6
Large Language Models (LLMs) are increasingly applied in various real-world scenarios due to their excellent generalization capabilities and robust generative abilities. However, t…
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang +10
This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prom…
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
Huiqiang Jiang, Qianhui Wu, Xufang Luo +4
In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM…
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin +2
Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) promp…
CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition
Tingting Ma, Qianhui Wu, Huiqiang Jiang +3
Cross-lingual named entity recognition (NER) aims to train an NER system that generalizes well to a target language by leveraging labeled data in a given source language. Previous…
Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text
Qianhui Wu, Huiqiang Jiang, Haonan Yin +2
Self-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-distribution (ID) examples. These ap…
Decomposed Meta-Learning for Few-Shot Named Entity Recognition
Tingting Ma, Huiqiang Jiang, Qianhui Wu +2
Few-shot named entity recognition (NER) systems aim at recognizing novel-class named entities based on only a few labeled examples. In this paper, we present a decomposed meta-lear…
AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER
Weile Chen, Huiqiang Jiang, Qianhui Wu +2
Neural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always availab…
UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data
Qianhui Wu, Zijia Lin, Börje F. Karlsson +2
Prior works in cross-lingual named entity recognition (NER) with no/little labeled data fall into two primary categories: model transfer based and data transfer based methods. In t…
Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language
Qianhui Wu, Zijia Lin, Börje F. Karlsson +2
To better tackle the named entity recognition (NER) problem on languages with little/no labeled data, cross-lingual NER must effectively leverage knowledge learned from source lang…
Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources
Qianhui Wu, Zijia Lin, Guoxin Wang +4
For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing metho…