Search Results for author:
Found 19 papers, 13 papers with code
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences.
CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
Similarity-based retrieval often has low recall in complex tasks, while manual tools and APIs are typically task-specific and require expert knowledge, reducing their generalizability across diverse code tasks and real-world applications.
MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
To address these problems, we propose MAMA, a new approach to learning video-language representations by utilizing a contrastive objective with a subtractive angular margin to regularize cross-modal representations in their effort to reach perfect similarity.
Encoding and Controlling Global Semantics for Long-form Video Question Answering
Seeking answers effectively for long videos is essential to build video question answering (videoQA) systems.
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
In the face of uncertainty, the ability to *seek information* is of fundamental importance.
READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization.
MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration
Large Language Models (LLMs) have marked a significant advancement in the field of natural language processing, demonstrating exceptional capabilities in reasoning, tool usage, and memory.
Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals
Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practical scenarios.
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
To better break down the problem, we define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency.
Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System
This approach uses LLM as annotation-free user simulator to assess dialogue responses, combining them with smaller fine-tuned end-to-end TOD models.
POP: Prompt Of Prompts for Continual Learning
We show that a foundation model equipped with POP learning is able to outperform classic CL methods by a significant margin.
Modeling User Satisfaction Dynamics in Dialogue via Hawkes Process
It assumes that the performance of a dialogue system can be measured by user satisfaction and uses an estimator to simulate users.
Taxonomic Class Incremental Learning
In this work, we propose the Taxonomic Class Incremental Learning (TCIL) problem.
Dense Network Expansion for Class Incremental Learning
This is accomplished by the introduction of dense connections between the intermediate layers of the task expert networks, that enable the transfer of knowledge from old to new tasks via feature sharing and reusing.
Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction
Our proposed approach achieves state-of-the-art performance in simulated high-dimensional and dynamic tasks while avoiding collisions with the environment.
Unlocking the Full Potential of Small Data with Diverse Supervision
Indeed, even the majority of few-shot learning methods rely on a large set of "base classes" for pretraining.
Mining Unfollow Behavior in Large-Scale Online Social Networks via Spatial-Temporal Interaction
Next, we define user's attributes as two categories: spatial attributes (e. g., social role of user) and temporal attributes (e. g., post content of user).
Syntax Encoding with Application in Authorship Attribution
We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation.
