Search Results for author:
Found 42 papers, 15 papers with code
ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
This work provides essential insights and tools for advancing forward pass methods to overcome forgetting.
ResearchTown: Simulator of Human Research Community
Our experiments reveal three key findings: (1) ResearchTown can provide a realistic simulation of collaborative research activities, including paper writing and review writing; (2) ResearchTown can maintain robust simulation with multiple researchers and diverse papers; (3) ResearchTown can generate interdisciplinary research ideas that potentially inspire novel research directions.
PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis
Furthermore, we integrate the audio-point enhancement module, which not only ensures the synchronization of the audio signal with the corresponding lip point cloud within the feature space, but also facilitates a deeper understanding of the interrelations among cross-modal conditional features.
Task-driven Image Fusion with Learnable Fusion Loss
This module is supervised by the loss of downstream tasks in a meta-learning manner.
CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis
Our method offers precise control over both the spatial attributes (polyp location and shape) and clinical characteristics of polyps that align with clinical descriptions.
Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs
In this paper, we propose \textit{graph of records} (\textbf{GoR}), which leverages historical responses generated by LLMs to enhance RAG for long-context global summarization.
GraphRouter: A Graph-based Router for LLM Selections
The rapidly growing number and variety of Large Language Models (LLMs) present significant challenges in efficiently selecting the appropriate LLM for a given query, especially considering the trade-offs between performance and computational cost.
Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance
As scientific research proliferates, researchers face the daunting task of navigating and reading vast amounts of literature.
Learning in Order! A Sequential Strategy to Learn Invariant Features for Multimodal Sentiment Analysis
This work proposes a novel and simple sequential learning strategy to train models on videos and texts for multimodal sentiment analysis.
BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems
Compared to single agents, multi-agent systems have higher requirements for the collaboration capabilities of language models.
From Pre-training Corpora to Large Language Models: What Factors Influence LLM Performance in Causal Discovery Tasks?
Recent advances in artificial intelligence have seen Large Language Models (LLMs) demonstrate notable proficiency in causal discovery tasks.
Solving the Model Unavailable MARE using Q-Learning Algorithm
In this paper, the discrete-time modified algebraic Riccati equation (MARE) is solved when the system model is completely unavailable.
CausalScore: An Automatic Reference-Free Metric for Assessing Response Relevance in Open-Domain Dialogue Systems
Automatically evaluating the quality of responses in open-domain dialogue systems is a challenging but crucial task.
Causal Discovery Inspired Unsupervised Domain Adaptation for Emotion-Cause Pair Extraction
Inspired by causal discovery, we propose a novel deep latent model in the variational autoencoder (VAE) framework, which not only captures the underlying latent structures of data but also utilizes the easily transferable knowledge of emotions as the bridge to link the distributions of events in different domains.
How Far Are We From AGI: Are LLMs All We Need?
The evolution of artificial intelligence (AI) has profoundly impacted human society, driving significant advancements in multiple sectors.
Revisiting Neural Networks for Continual Learning: An Architectural Perspective
This paper seeks to bridge this gap between network architecture design and CL, and to present a holistic study on the impact of network architectures on CL.
IMO: Greedy Layer-Wise Sparse Representation Learning for Out-of-Distribution Text Classification with Pre-trained Models
Machine learning models have made incredible progress, but they still struggle when applied to examples from unseen domains.
Constructing Data Transaction Chains Based on Opportunity Cost Exploration
However, the inherent replicability and privacy concerns of data make it challenging to directly apply traditional trading theories to data markets.
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.
Deep Reinforcement Learning for Modelling Protein Complexes
In this work, by taking each chain as a node and assembly actions as edges, we show that an acyclic undirected connected graph can be used to predict the structure of multi-chain protein complexes (a. k. a., protein complex modelling, PCM).
RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations
While collecting sufficient human-authored data is costly, synthetic conversations provide suitable amounts of data to help mitigate the scarcity of training data, as well as the chance to assess the alignment between LLMs and humans in the awareness of social norms.
Let's Negotiate! A Survey of Negotiation Dialogue Systems
Negotiation is a crucial ability in human communication.
SADAS: A Dialogue Assistant System Towards Remediating Norm Violations in Bilingual Socio-Cultural Conversations
We have released our code and software at:~\url{https://github. com/AnonymousEACLDemo/SADAS}.
InstructVideo: Instructing Video Diffusion Models with Human Feedback
To tackle this problem, we propose InstructVideo to instruct text-to-video diffusion models with human feedback by reward fine-tuning.
RDBench: ML Benchmark for Relational Databases
Benefiting from high-quality datasets and standardized evaluation metrics, machine learning (ML) has achieved sustained progress and widespread applications.
Molecular De Novo Design through Transformer-based Reinforcement Learning
In contrast to the traditional RNN-based models, our proposed method exhibits superior performance in generating compounds predicted to be active against various biological targets, capturing long-term dependencies in the molecular structure sequence.
CITING: Large Language Models Create Curriculum for Instruction Tuning
Specifically, we employ a teacher LLM to create a curriculum for instruction tuning of the student LLM, namely Curriculum Instruction TunING (CITING).
RLIPv2: Fast Scaling of Relational Language-Image Pre-training
In this paper, we propose RLIPv2, a fast converging model that enables the scaling of relational pre-training to large-scale pseudo-labelled scene graph data.
Ranked #1 on
Zero-Shot Human-Object Interaction Detection
on HICO-DET
(using extra training data)
Towards Efficient Deep Hashing Retrieval: Condensing Your Data via Feature-Embedding Matching
The expenses involved in training state-of-the-art deep hashing retrieval models have witnessed an increase due to the adoption of more sophisticated models and large-scale datasets.
Refined Response Distillation for Class-Incremental Player Detection
Furthermore, we present the NBA-IOD and Volleyball-IOD datasets as the benchmark and investigate the IOD tasks of the players systematically.
SocialDial: A Benchmark for Socially-Aware Dialogue Systems
To the best of our knowledge, SocialDial is the first socially-aware dialogue dataset that covers multiple social factors and has fine-grained labels.
Cultural Vocal Bursts Intensity Prediction
Synthetic Data Generation
Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery
In this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDIALOG curated in our work.
Let's Negotiate! A Survey of Negotiation Dialogue Systems
Negotiation is one of the crucial abilities in human communication, and there has been a resurgent research interest in negotiation dialogue systems recently, which goal is to empower intelligent agents with such ability that can efficiently help humans resolve conflicts or reach beneficial agreements.
Progressive Learning without Forgetting
Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks.
Efficient Demand Response Location Targeting for Price Spike Mitigation by Exploiting Price-demand Relationship
We formulate a bilevel program where the upper level determines the DR locations and demand reductions while ensuring the average nodal prices meet a predetermined target.
RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection
The task of Human-Object Interaction (HOI) detection targets fine-grained visual parsing of humans interacting with their environment, enabling a broad range of applications.
Ranked #17 on
Human-Object Interaction Detection
on HICO-DET
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.
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.
Deep Reinforcement Learning for Demand Driven Services in Logistics and Transportation Systems: A Survey
For each problem, we comprehensively introduce the existing DRL solutions.
Few-Shot Conversational Dense Retrieval
In this paper, we present a Conversational Dense Retrieval system, ConvDR, that learns contextualized embeddings for multi-turn conversational queries and retrieves documents solely using embedding dot products.
Reinforced Contact Tracing and Epidemic Intervention
In this paper, we develop an Individual-based Reinforcement Learning Epidemic Control Agent (IDRLECA) to search for smart epidemic control strategies that can simultaneously minimize infections and the cost of mobility intervention.
On codes in the projective linear group $PGL(2,q)$
In this paper, we resolve a conjecture of Green and Liebeck [Disc.
Combinatorics
