Search Results for author:
Found 23 papers, 15 papers with code
AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
As AI models are increasingly deployed across diverse real-world scenarios, ensuring their safety remains a critical yet underexplored challenge.
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
For the first time, our model SnapGen, demonstrates the generation of 1024x1024 px images on a mobile device around 1. 4 seconds.
Ranked #11 on
Text-to-Image Generation
on GenEval
Synth-Empathy: Towards High-Quality Synthetic Empathy Data
In recent years, with the rapid advancements in large language models (LLMs), achieving excellent empathetic response capabilities has become a crucial prerequisite.
SynthVLM: High-Efficiency and High-Quality Synthetic Data for Vision Language Models
Crucially, our method's reliance on purely generated data ensures the preservation of privacy, achieving SoTA performance with just 100k data points (only 18% of the official dataset size).
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the weights in Large Language Models (LLMs).
KeyVideoLLM: Towards Large-scale Video Keyframe Selection
Recently, with the rise of web videos, managing and understanding large-scale video datasets has become increasingly important.
Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
Security concerns related to Large Language Models (LLMs) have been extensively explored, yet the safety implications for Multimodal Large Language Models (MLLMs), particularly in medical contexts (MedMLLMs), remain insufficiently studied.
Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers
Non-linear functions are prevalent in Transformers and their lightweight variants, incurring substantial and frequently underestimated hardware costs.
AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation
Text-to-Image (T2I) diffusion models have achieved remarkable success in image generation.
CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels
However, a major doubt about online learning is whether students are as engaged as they are in face-to-face classes.
Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning
In this work, we propose CoT-Influx, a novel approach that pushes the boundary of few-shot Chain-of-Thoughts (CoT) learning to improve LLM mathematical reasoning.
Ranked #117 on
Arithmetic Reasoning
on GSM8K
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
Our method, for the first time, can quantize both weights and activations in the LLaMA-13B to only 4-bit and achieves an average score of 63. 1 on the common sense zero-shot reasoning tasks, which is only 5. 8 lower than the full-precision model, significantly outperforming the previous state-of-the-art by 12. 7 points.
VideoPro: A Visual Analytics Approach for Interactive Video Programming
Constructing supervised machine learning models for real-world video analysis require substantial labeled data, which is costly to acquire due to scarce domain expertise and laborious manual inspection.
Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
We explore the best practices to alleviate the variation's influence during low-bit transformer QAT and propose a variation-aware quantization scheme for both vision and language transformers.
Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection
Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations.
SDQ: Stochastic Differentiable Quantization with Mixed Precision
In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used.
FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation
To relax this assumption, in this work, we propose a label-agnostic unified federated learning framework, named FedMix, for medical image segmentation based on mixed image labels.
Joint stereo 3D object detection and implicit surface reconstruction
We present a new learning-based framework S-3D-RCNN that can recover accurate object orientation in SO(3) and simultaneously predict implicit rigid shapes from stereo RGB images.
Transferable Interactiveness Knowledge for Human-Object Interaction Detection
Human-Object Interaction (HOI) detection is an important problem to understand how humans interact with objects.
Ranked #28 on
Human-Object Interaction Detection
on V-COCO
PaStaNet: Toward Human Activity Knowledge Engine
In light of this, we propose a new path: infer human part states first and then reason out the activities based on part-level semantics.
Ranked #3 on
Human-Object Interaction Detection
on HICO
NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations
NeuronInspect first identifies the existence of backdoor attack targets by generating the explanation heatmap of the output layer.
HAKE: Human Activity Knowledge Engine
To address these and promote the activity understanding, we build a large-scale Human Activity Knowledge Engine (HAKE) based on the human body part states.
Ranked #2 on
Human-Object Interaction Detection
on HICO
(using extra training data)
Transferable Interactiveness Knowledge for Human-Object Interaction Detection
On account of the generalization of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results.
Ranked #29 on
Human-Object Interaction Detection
on V-COCO
