Search Results for author:
Found 61 papers, 34 papers with code
Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning
Adversarial robustness has attracted much attention recently, and the mainstream solution is adversarial training.
PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack
To reduce the potential side effects of using defense modules, we further propose a novel forgetting restricted adversarial training, which filters out bad adversarial examples that impair the performance of original ones.
Improving RL Exploration for LLM Reasoning through Retrospective Replay
We observe that for complex problems, during the early stages of training, the model exhibits strong exploratory capabilities and can identify promising solution ideas.
ImplicitCell: Resolution Cell Modeling of Joint Implicit Volume Reconstruction and Pose Refinement in Freehand 3D Ultrasound
Freehand 3D ultrasound enables volumetric imaging by tracking a conventional ultrasound probe during freehand scanning, offering enriched spatial information that improves clinical diagnosis.
Better Process Supervision with Bi-directional Rewarding Signals
Process supervision, i. e., evaluating each step, is critical for complex large language model (LLM) reasoning and test-time searching with increased inference compute.
Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge
Furthermore, no open-source dataset is currently available to support the development of multi-class aortic segmentation methods.
CDI: Blind Image Restoration Fidelity Evaluation based on Consistency with Degraded Image
In stead of directly comparing a restored image with a reference image, the BIR IQA evaluates fidelity by calculating the Consistency with Degraded Image (CDI).
Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Experiments show that the method improves the actor's exploration efficiency and solution diversity, especially on challenging queries, leading to a stronger reasoning model.
Multi-Programming Language Sandbox for LLMs
We introduce MPLSandbox, an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Our findings indicate that the ability to prevent sycophancy is predominantly observed in higher layers of the model.
RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
However, the current evaluation of RMs may not directly correspond to their alignment performance due to the limited distribution of evaluation data and evaluation methods that are not closely related to alignment objectives.
RoCoSDF: Row-Column Scanned Neural Signed Distance Fields for Freehand 3D Ultrasound Imaging Shape Reconstruction
However, the shape reconstruction of multi-view ultrasound data remains challenging due to the elevation distortion caused by thick transducer probes.
RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent
To enable context-aware and efficient red teaming, we abstract and model existing attacks into a coherent concept called "jailbreak strategy" and propose a multi-agent LLM system named RedAgent that leverages these strategies to generate context-aware jailbreak prompts.
What's Wrong with Your Code Generated by Large Language Models? An Extensive Study
The increasing development of large language models (LLMs) in code generation has drawn significant attention among researchers.
SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research.
SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
To address these limitations, we propose a Safety Preference Alignment dataset for Vision Language Models named SPA-VL.
Aligning Large Language Models from Self-Reference AI Feedback with one General Principle
In aligning large language models (LLMs), utilizing feedback from existing advanced AI rather than humans is an important method to scale supervisory signals.
Toward Optimal LLM Alignments Using Two-Player Games
We theoretically demonstrate that this iterative reinforcement learning optimization converges to a Nash Equilibrium for the game induced by the agents.
Uncertainty Aware Learning for Language Model Alignment
As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges.
AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community.
Reliable Source Approximation: Source-Free Unsupervised Domain Adaptation for Vestibular Schwannoma MRI Segmentation
Source-Free Unsupervised Domain Adaptation (SFUDA) has recently become a focus in the medical image domain adaptation, as it only utilizes the source model and does not require annotated target data.
MetaRM: Shifted Distributions Alignment via Meta-Learning
These two issues can be united as a challenge posed by the shifted distribution of the environment.
DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction
Additionally, it effectively augments the feasibility of the solution space for the inverse problem through the generative diffusion model, resulting in increased stability and precision in the solutions.
Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals
We first empirically show that the features of either clean signals or adversarial perturbations are redundant and span in low-dimensional linear subspaces respectively with minimal overlap, and the classical low-dimensional subspace projection can suppress perturbation features out of the subspace of clean signals.
EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against LLMs.
Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences.
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
We construct the DACO dataset, containing (1) 440 databases (of tabular data) collected from real-world scenarios, (2) ~2k query-answer pairs that can serve as weak supervision for model training, and (3) a concentrated but high-quality test set with human refined annotations that serves as our main evaluation benchmark.
Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution
To address this issue, we propose a cost-effective preference learning strategy, optimizing reward models by distinguishing between human and machine translations.
Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices
Moreover, the models trained on standard ultrasound device data are constrained by training data distribution and perform poorly when directly applied to handheld device data.
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models.
StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
The advancement of large language models (LLMs) has significantly propelled the field of code generation.
MouSi: Poly-Visual-Expert Vision-Language Models
This technique introduces a fusion network to unify the processing of outputs from different visual experts, while bridging the gap between image encoders and pre-trained LLMs.
Ranked #124 on
Visual Question Answering
on MM-Vet
Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
This reliance limits the applicability of RLHF and hinders the development of professional assistants tailored to diverse human preferences.
Neural Implicit Surface Reconstruction of Freehand 3D Ultrasound Volume with Geometric Constraints
Three-dimensional (3D) freehand ultrasound (US) is a widely used imaging modality that allows non-invasive imaging of medical anatomy without radiation exposure.
Secrets of RLHF in Large Language Models Part II: Reward Modeling
We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset and fully leverage high-quality preference data.
Automatic bony structure segmentation and curvature estimation on ultrasound cervical spine images -- a feasibility study
In this study, a portable ultrasound imaging system was applied to acquire cervical spine image volume.
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks.
Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation
This method trains the model to prioritize the best responses from a pool of candidates created for a particular task.
Orthogonal Subspace Learning for Language Model Continual Learning
In this paper, we propose orthogonal low-rank adaptation (O-LoRA), a simple and efficient approach for continual learning in language models, effectively mitigating catastrophic forgetting while learning new tasks.
Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
In this work, we propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
RealBehavior: A Framework for Faithfully Characterizing Foundation Models' Human-like Behavior Mechanisms
Reports of human-like behaviors in foundation models are growing, with psychological theories providing enduring tools to investigate these behaviors.
TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
In this paper, we introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback serves as a crucial bridge, aligning large language models with human and societal values.
The Rise and Potential of Large Language Model Based Agents: A Survey
Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks.
Secrets of RLHF in Large Language Models Part I: PPO
Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
To enhance the multi-step reasoning capabilities of large language models, researchers have extensively explored prompting methods, notably the Chain-of-Thought (CoT) method which explicitly elicits human-like rationales.
Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
Models trained with empirical risk minimization (ERM) are revealed to easily rely on spurious correlations, resulting in poor generalization.
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild
The principle of continual relation extraction~(CRE) involves adapting to emerging novel relations while preserving od knowledge.
InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
Large language models have unlocked strong multi-task capabilities from reading instructive prompts.
Ranked #3 on
Zero-shot Named Entity Recognition (NER)
on CrossNER
(using extra training data)
How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
The GPT-3. 5 models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks, showcasing their strong understanding and reasoning capabilities.
Natural Language Inference
Natural Language Understanding
+1
Automatic Diagnosis of Carotid Atherosclerosis Using a Portable Freehand 3D Ultrasound Imaging System
A total of 127 3D carotid artery scans were acquired using a portable 3D US system which consisted of a handheld US scanner and an electromagnetic tracking system.
VertMatch: A Semi-supervised Framework for Vertebral Structure Detection in 3D Ultrasound Volume
We propose VertMatch, a two-step framework to detect vertebral structures in 3D ultrasound volume by utilizing unlabeled data in semi-supervised manner.
Efficient Adversarial Training with Robust Early-Bird Tickets
Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs).
Robust Lottery Tickets for Pre-trained Language Models
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.
TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
The proposed method underscores the significance of multi-task learning and explicit cross-task consistency enhancement for advancing semantic segmentation and highlights the potential of multitasking in real-time semantic segmentation.
Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline
We also propose a new 3D VQA framework to effectively predict the completely visually grounded and explainable answer.
Automatic spinal curvature measurement on ultrasound spine images using Faster R-CNN
The framework consisted of two closely linked modules: 1) the lamina detector for identifying and locating each lamina pairs on ultrasound coronal images, and 2) the spinal curvature estimator for calculating the scoliotic angles based on the chain of detected lamina.
Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective
Most of the existing debiasing methods often identify and weaken these samples with biased features (i. e., superficial surface features that cause such spurious correlations).
Automatic segmentation of vertebral features on ultrasound spine images using Stacked Hourglass Network
Methods: The network was trained to detect vertebral SP and laminae as five landmarks on 1200 ultrasound transverse images and validated on 100 images.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one.
Cardea: Context-Aware Visual Privacy Protection from Pervasive Cameras
The growing popularity of mobile and wearable devices with built-in cameras, the bright prospect of camera related applications such as augmented reality and life-logging system, the increased ease of taking and sharing photos, and advances in computer vision techniques have greatly facilitated people's lives in many aspects, but have also inevitably raised people's concerns about visual privacy at the same time.
