Search Results for author:
Found 12 papers, 7 papers with code
From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
The outstanding capabilities of large language models (LLMs) render them a crucial component in various autonomous agent systems.
HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
To alleviate this problem, we propose HtmlRAG, which uses HTML instead of plain text as the format of retrieved knowledge in RAG.
Nova: A Practical and Advanced Alignment
Importantly, Qwen2-Nova-72B and Llama3-PBM-Nova-70B are instruct versions of the Qwen2-72B and Llama-3-70B base models, optimized through Nova.
RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation
These ranked documents sufficiently cover various query aspects and are aware of the generator's preferences, hence incentivizing it to produce rich and comprehensive responses for users.
Make Continual Learning Stronger via C-Flat
A general framework of C-Flat applied to all CL categories and a thorough comparison with loss minima optimizer and flat minima based CL approaches is presented in this paper, showing that our method can boost CL performance in almost all cases.
Baichuan 2: Open Large-scale Language Models
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
Progressive Learning without Forgetting
Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks.
Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation
In this paper, we propose a response-based incremental distillation method, dubbed Elastic Response Distillation (ERD), which focuses on elastically learning responses from the classification head and the regression head.
Crafting Better Contrastive Views for Siamese Representation Learning
For high performance Siamese representation learning, one of the keys is to design good contrastive pairs.
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics
Specifically, We propose to utilize a Verb Semantic Model (VSM) and use semantic aggregation to profit from this object-guided hierarchy.
Ranked #5 on
Human-Object Interaction Detection
on V-COCO
Response-based Distillation for Incremental Object Detection
However, fine-tuning directly on a well-trained detection model with only new data will leads to catastrophic forgetting.
Spatio-Temporal Dynamic Inference Network for Group Activity Recognition
Within each interaction field, we apply DR to predict the relation matrix and DW to predict the dynamic walk offsets in a joint-processing manner, thus forming a person-specific interaction graph.
Ranked #3 on
Group Activity Recognition
on Volleyball
