Search Results for author:
Found 73 papers, 27 papers with code
High-quality Single-model Deep Video Compression with Frame-Conv3D and Multi-frame Differential Modulation
This paper proposes a deep video compression method to simultaneously encode multiple frames with Frame-Conv3D and differential modulation.
DRE: An Effective Dual-Refined Method for Integrating Small and Large Language Models in Open-Domain Dialogue Evaluation
To leverage their complementary strengths, we introduce SLIDE (Small and Large Integrated for Dialogue Evaluation), a method integrating SLMs and LLMs via adaptive weighting.
UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines
Traditional spatiotemporal models generally rely on task-specific architectures, which limit their generalizability and scalability across diverse tasks due to domain-specific design requirements.
Optimal Transport Adapter Tuning for Bridging Modality Gaps in Few-Shot Remote Sensing Scene Classification
Central to this approach is the Optimal Transport Adapter (OTA), which employs a cross-modal attention mechanism to enrich textual representations and facilitate subsequent better information interaction.
SurveyX: Academic Survey Automation via Large Language Models
Large Language Models (LLMs) have demonstrated exceptional comprehension capabilities and a vast knowledge base, suggesting that LLMs can serve as efficient tools for automated survey generation.
DERMARK: A Dynamic, Efficient and Robust Multi-bit Watermark for Large Language Models
In this paper, we derive the watermark embedding distribution based on the logits of LLMs and propose a formal inequality to segment the text optimally for watermark embedding.
GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism
Additionally, this study explores a novel recurrent routing strategy that may inspire further advancements in enhancing the reasoning capabilities of language models.
JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration
The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance and efficiency, particularly for model deployment on resource-constrained edge devices.
EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
We propose EVOlutionary Selector (EVOS), an efficient training paradigm for accelerating Implicit Neural Representation (INR).
SpecFuse: Ensembling Large Language Models via Next-Segment Prediction
In this paper, we propose SpecFuse, a novel ensemble framework that outputs the fused result by iteratively producing the next segment through collaboration among LLMs.
SizeGS: Size-aware Compression of 3D Gaussians with Hierarchical Mixed Precision Quantization
Using the size estimator and MPQ, we develop a calibrated algorithm to identify optimal hyperparameters in just 10 minutes, achieving a 1. 69$\times$ efficiency increase with quality comparable to state-of-the-art methods.
GAQAT: gradient-adaptive quantization-aware training for domain generalization
To address this limitation, we propose a novel Gradient-Adaptive Quantization-Aware Training (GAQAT) framework for DG.
MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation
More specifically, we first replace rotation quaternions with Euler angles; then, we apply region adaptive hierarchical transform to key attributes to reduce entropy.
Expansive Supervision for Neural Radiance Field
Neural Radiance Field (NeRF) has achieved remarkable success in creating immersive media representations through its exceptional reconstruction capabilities.
RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization
To address these limitations, we propose efficient unsupervised domain adaptation with ReTraining-Free Quantization (RTF-Q).
Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes
Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of sophisticated robotic behaviors.
PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference
We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs.
HGNET: A Hierarchical Feature Guided Network for Occupancy Flow Field Prediction
Additionally, to enhance the temporal consistency and causal relationships of the predictions, we propose a Time Series Memory framework to learn the conditional distribution models of the prediction outputs at future time steps from multivariate time series.
BioMNER: A Dataset for Biomedical Method Entity Recognition
Named entity recognition (NER) stands as a fundamental and pivotal task within the realm of Natural Language Processing.
Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
Recent advancements in diffusion models, particularly the architectural transformation from UNet-based models to Diffusion Transformers (DiTs), significantly improve the quality and scalability of image and video generation.
Crafting Customisable Characters with LLMs: Introducing SimsChat, a Persona-Driven Role-Playing Agent Framework
Large Language Models (LLMs) demonstrate remarkable ability to comprehend instructions and generate human-like text, enabling sophisticated agent simulation beyond basic behavior replication.
MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention
Instead of inferring the complete human behavior characteristics, MEReQ infers a residual reward function that captures the discrepancy between the human expert's and the prior policy's underlying reward functions.
Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox
Based on this benchmark, we conduct extensive experiments with two well-known LLMs (English and Chinese) and four quantization algorithms to investigate this topic in-depth, yielding several counter-intuitive and valuable findings, e. g., models quantized using a calibration set with the same distribution as the test data are not necessarily optimal.
STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargeting
The creation of 4D avatars (i. e., animated 3D avatars) from text description typically uses text-to-image (T2I) diffusion models to synthesize 3D avatars in the canonical space and subsequently applies animation with target motions.
Causal prompting model-based offline reinforcement learning
To tackle these issues, we introduce the Causal Prompting Reinforcement Learning (CPRL) framework, designed for highly suboptimal and resource-constrained online scenarios.
One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments
Large Language Models (LLMs) have advanced rapidly but face significant memory demands.
SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation
Our approach introduces several techniques: (1) Contrastive learning to differentiate between robust and non-robust response embeddings; (2) A novel metric for semantic sensitivity that combines embedding cosine distances with similarity learned through neural networks, and (3) a strategy for incorporating the evaluation results from both the SLM and LLMs.
TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
Diffusion models have emerged as preeminent contenders in the realm of generative models.
Investigating the Impact of Quantization on Adversarial Robustness
Quantization is a promising technique for reducing the bit-width of deep models to improve their runtime performance and storage efficiency, and thus becomes a fundamental step for deployment.
Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation
Trainable evaluation metrics, typically trained with true positive and randomly selected negative responses, tend to assign higher scores to responses that share greater content similarity with a given context.
Train & Constrain: Phonologically Informed Tongue-Twister Generation from Topics and Paraphrases
Previous work in phonologically and phonetically grounded language generation has mainly focused on domains such as puns and poetry.
BeTAIL: Behavior Transformer Adversarial Imitation Learning from Human Racing Gameplay
Thus, we propose BeTAIL: Behavior Transformer Adversarial Imitation Learning, which combines a Behavior Transformer (BeT) policy from human demonstrations with online AIL.
Retraining-free Model Quantization via One-Shot Weight-Coupling Learning
Conversely, mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers.
A Cross-Attention Augmented Model for Event-Triggered Context-Aware Story Generation
These results underscore the effectiveness of our model in leveraging context and event features to improve the quality of generated narratives.
GlanceSeg: Real-time microaneurysm lesion segmentation with gaze-map-guided foundation model for early detection of diabetic retinopathy
In this work, we propose a human-in-the-loop, label-free early DR diagnosis framework called GlanceSeg, based on SAM.
Data-Aware Gradient Compression for FL in Communication-Constrained Mobile Computing
Recognizing the computational limitations of mobile devices, we propose the DAGC-A, which is computationally less demanding and enhances the robustness of compression in non-IID scenarios.
Active Exploration in Iterative Gaussian Process Regression for Uncertainty Modeling in Autonomous Racing
In the exploration, a MPC collects diverse data by balancing the racing objectives and the exploration criterion; then the GP is re-trained.
ACL Anthology Helper: A Tool to Retrieve and Manage Literature from ACL Anthology
This paper presents a tool called ``ACL Anthology Helper''.
Enhancing Biomedical Lay Summarisation with External Knowledge Graphs
Previous approaches for automatic lay summarisation are exclusively reliant on the source article that, given it is written for a technical audience (e. g., researchers), is unlikely to explicitly define all technical concepts or state all of the background information that is relevant for a lay audience.
Improving Biomedical Abstractive Summarisation with Knowledge Aggregation from Citation Papers
Abstracts derived from biomedical literature possess distinct domain-specific characteristics, including specialised writing styles and biomedical terminologies, which necessitate a deep understanding of the related literature.
Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization
We observe that, generally, a more diverse set of co-play agents during training enhances the generalization performance of the ego agent; however, this improvement varies across distinct scenarios and environments.
Effective Distillation of Table-based Reasoning Ability from LLMs
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks.
Improving Medical Dialogue Generation with Abstract Meaning Representations
In this paper, We propose a novel framework that models dialogues between patients and healthcare professionals using AMR graphs, where the neural networks incorporate textual and graphical knowledge with a dual attention mechanism.
Pre-training on Synthetic Driving Data for Trajectory Prediction
Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving.
Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration
GOLD distills an offline DT policy into a lightweight policy network through guided online safe RL training, which outperforms both the offline DT policy and online safe RL algorithms.
Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation
Further analysis also shows that our representation learning framework can fill the semantic gap by coagulating representations of both text and graph knowledge.
Residual Q-Learning: Offline and Online Policy Customization without Value
Specifically, we formulate the customization problem as a Markov Decision Process (MDP) with a reward function that combines 1) the inherent reward of the demonstration; and 2) the add-on reward specified by the downstream task.
Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning
Our Skill-Critic algorithm optimizes both the low-level and high-level policies; these policies are initialized and regularized by the latent space learned from offline demonstrations to guide the parallel policy optimization.
TwistList: Resources and Baselines for Tongue Twister Generation
Previous work in phonetically-grounded language generation has mainly focused on domains such as lyrics and poetry.
Knowledge Soft Integration for Multimodal Recommendation
To address this issue, we propose using knowledge soft integration to balance the utilization of multimodal features and the curse of knowledge problem it brings about.
CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation
Commonsense knowledge is crucial to many natural language processing tasks.
Eye tracking guided deep multiple instance learning with dual cross-attention for fundus disease detection
Concretely, the HITL CAD system was implemented on the multiple instance learning (MIL), where eye-tracking gaze maps were beneficial to cherry-pick diagnosis-related instances.
Click-aware Structure Transfer with Sample Weight Assignment for Post-Click Conversion Rate Estimation
To tackle this issue, we argue that a trade-off should be achieved between the introduction of large amounts of auxiliary information and the protection of valuable information related to CVR.
Editing Driver Character: Socially-Controllable Behavior Generation for Interactive Traffic Simulation
To ensure that autonomous vehicles take safe and efficient maneuvers in different interactive traffic scenarios, we should be able to evaluate autonomous vehicles against reactive agents with different social characteristics in the simulation environment.
ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices
However, prior supernet training methods that rely on uniform sampling suffer from the gradient conflict issue: the sampled subnets can have vastly different model sizes (e. g., 50M vs. 2G FLOPs), leading to different optimization directions and inferior performance.
SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization
This general and dataset-independent property makes us search for the MPQ policy over a rather small-scale proxy dataset and then the policy can be directly used to quantize the model trained on a large-scale dataset.
Terminology-aware Medical Dialogue Generation
In this paper, we propose a novel framework to improve medical dialogue generation by considering features centered on domain-specific terminology.
EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention
One of the key challenges of automatic story generation is how to generate a long narrative that can maintain fluency, relevance, and coherence.
NGEP: A Graph-based Event Planning Framework for Story Generation
To improve the performance of long text generation, recent studies have leveraged automatically planned event structures (i. e. storylines) to guide story generation.
Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics
In spite of the success of prior works with the application of pre-trained models, current neural models for Chinese stories still struggle to generate high-quality long text narratives.
PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map
It is hard to replicate these approaches in trajectory forecasting due to the lack of adequate trajectory data (e. g., 34K samples in the nuScenes dataset).
Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach
We propose to feed different data samples with varying quantization schemes to achieve a data-dependent dynamic inference, at a fine-grained layer level.
Interventional Behavior Prediction: Avoiding Overly Confident Anticipation in Interactive Prediction
Moreover, to properly evaluate an IBP model with offline datasets, we propose a Shapley-value-based metric to verify if the prediction model satisfies the inherent temporal independence of an interventional distribution.
Domain Knowledge Driven Pseudo Labels for Interpretable Goal-Conditioned Interactive Trajectory Prediction
To address these issues, we propose a novel approach to avoid KL vanishing and induce an interpretable interactive latent space with pseudo labels.
Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
For example, MPQ search on ResNet18 with our indicators takes only 0. 06 s, which improves time efficiency exponentially compared to iterative search methods.
Recent Advances in Neural Text Generation: A Task-Agnostic Survey
In recent years, considerable research has been dedicated to the application of neural models in the field of natural language generation (NLG).
Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling
In this work, we argue that one of the typical formulations of VAEs in multi-agent modeling suffers from an issue we refer to as social posterior collapse, i. e., the model is prone to ignoring historical social context when predicting the future trajectory of an agent.
Dealing with the Unknown: Pessimistic Offline Reinforcement Learning
Reinforcement Learning (RL) has been shown effective in domains where the agent can learn policies by actively interacting with its operating environment.
Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving
Explainability is essential for autonomous vehicles and other robotics systems interacting with humans and other objects during operation.
Adaptive Pixel-wise Structured Sparse Network for Efficient CNNs
To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image.
Adaptive Probabilistic Vehicle Trajectory Prediction Through Physically Feasible Bayesian Recurrent Neural Network
Current methods for long-term trajectory prediction cannot guarantee the physical feasibility of predicted distribution.
ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations
Learning from demonstrations is a popular tool for accelerating and reducing the exploration requirements of reinforcement learning.
Zero-shot Deep Reinforcement Learning Driving Policy Transfer for Autonomous Vehicles based on Robust Control
Although deep reinforcement learning (deep RL) methods have lots of strengths that are favorable if applied to autonomous driving, real deep RL applications in autonomous driving have been slowed down by the modeling gap between the source (training) domain and the target (deployment) domain.
