Search Results for author:
Found 41 papers, 15 papers with code
Baichuan-Omni-1.5 Technical Report
We introduce Baichuan-Omni-1. 5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities.
Fast-RF-Shimming: Accelerate RF Shimming in 7T MRI using Deep Learning
This approach offers a faster and more efficient solution to RF shimming challenges in UHF MRI.
SEG-SAM: Semantic-Guided SAM for Unified Medical Image Segmentation
First, to avoid the potential conflict between binary and semantic predictions, we introduce a semantic-aware decoder independent of SAM's original decoder, specialized for both semantic segmentation on the prompted object and classification on unprompted objects in images.
MC-LLaVA: Multi-Concept Personalized Vision-Language Model
Specifically, MC-LLaVA uses a joint training strategy incorporating multiple concepts in a single training step, allowing VLMs to perform accurately in multi-concept personalization.
EVQAScore: Efficient Video Question Answering Data Evaluation
To address this gap, we introduce EVQAScore, a reference-free method that leverages keyword extraction to assess both video caption and video QA data quality.
Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction
Document parsing is essential for converting unstructured and semi-structured documents-such as contracts, academic papers, and invoices-into structured, machine-readable data.
Baichuan Alignment Technical Report
Baichuan-Instruct is an internal model, while Qwen2-Nova-72B and Llama3-PBM-Nova-70B are instruct versions of the Qwen2-72B and Llama-3-70B base models, optimized through Baichuan Alignment.
Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning
While current research on function calling by LLMs primarily focuses on single-turn interactions, this paper addresses the overlooked necessity for LLMs to engage in multi-turn function calling--critical for handling compositional, real-world queries that require planning with functions but not only use functions.
Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models
During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora.
QAEncoder: Towards Aligned Representation Learning in Question Answering System
Modern QA systems entail retrieval-augmented generation (RAG) for accurate and trustworthy responses.
Data Proportion Detection for Optimized Data Management for Large Language Models
Large language models (LLMs) have demonstrated exceptional performance across a wide range of tasks and domains, with data preparation playing a critical role in achieving these results.
BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search
Large Language Models (LLMs) have exhibited exceptional performance across a broad range of tasks and domains.
Optimizing Transmit Field Inhomogeneity of Parallel RF Transmit Design in 7T MRI using Deep Learning
We propose a two-step deep learning strategy.
MathScape: Evaluating MLLMs in multimodal Math Scenarios through a Hierarchical Benchmark
To address this gap, we proposed MathScape, a new benchmark that emphasizes the understanding and application of combined visual and textual information.
CFBench: A Comprehensive Constraints-Following Benchmark for LLMs
The adeptness of Large Language Models (LLMs) in comprehending and following natural language instructions is critical for their deployment in sophisticated real-world applications.
Are Bigger Encoders Always Better in Vision Large Models?
Moreover, we analyzed the effects of LLM backbone parameter size and data quality on the pretraining outcomes.
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).
PAS: Data-Efficient Plug-and-Play Prompt Augmentation System
This combination of high performance, efficiency, and flexibility makes PAS a valuable system for enhancing the usability and effectiveness of LLMs through improved prompt engineering.
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.
Efficient-Empathy: Towards Efficient and Effective Selection of Empathy Data
By integrating sensibility and rationality data with a MoE structure, we achieve even higher performance, demonstrating the effectiveness of our Efficient-Empathy algorithm.
Hybrid Spatial-spectral Neural Network for Hyperspectral Image Denoising
Hyperspectral image (HSI) denoising is an essential procedure for HSI applications.
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.
A Survey of Multimodal Large Language Model from A Data-centric Perspective
Multimodal large language models (MLLMs) enhance the capabilities of standard large language models by integrating and processing data from multiple modalities, including text, vision, audio, video, and 3D environments.
Optimistic Thompson Sampling for No-Regret Learning in Unknown Games
This work tackles the complexities of multi-player scenarios in \emph{unknown games}, where the primary challenge lies in navigating the uncertainty of the environment through bandit feedback alongside strategic decision-making.
MC-NeRF: Multi-Camera Neural Radiance Fields for Multi-Camera Image Acquisition Systems
In this paper, we propose MC-NeRF, a method that enables joint optimization of both intrinsic and extrinsic parameters alongside NeRF.
Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation
We validate our method quantitatively by evaluating race and gender biases of three research-grade face recognition models.
A Distribution Optimization Framework for Confidence Bounds of Risk Measures
Unlike traditional approaches that add or subtract a confidence radius from the empirical risk measures, our proposed schemes evaluate a specific transformation of the empirical distribution based on the distance.
Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures
We study finite episodic Markov decision processes incorporating dynamic risk measures to capture risk sensitivity.
Visualizing chest X-ray dataset biases using GANs
Recent work demonstrates that images from various chest X-ray datasets contain visual features that are strongly correlated with protected demographic attributes like race and gender.
X-ray Recognition: Patient identification from X-rays using a contrastive objective
Recent research demonstrates that deep learning models are capable of precisely extracting bio-information (e. g. race, gender and age) from patients' Chest X-Rays (CXRs).
Linking convolutional kernel size to generalization bias in face analysis CNNs
Our framework is experimental, in that we train several versions of a network with an intervention to a specific hyperparameter, and measure the resulting causal effect of this choice on performance bias when a particular out-of-distribution image perturbation is applied.
Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds
We study the regret guarantee for risk-sensitive reinforcement learning (RSRL) via distributional reinforcement learning (DRL) methods.
Computational Efficiency
Distributional Reinforcement Learning
+3
Acoustic-Net: A Novel Neural Network for Sound Localization and Quantification
Acoustic source localization has been applied in different fields, such as aeronautics and ocean science, generally using multiple microphones array data to reconstruct the source location.
RareGAN: Generating Samples for Rare Classes
We study the problem of learning generative adversarial networks (GANs) for a rare class of an unlabeled dataset subject to a labeling budget.
False Data Injection Attack on Electric Vehicle-Assisted Voltage Regulation
With the large scale penetration of electric vehicles (EVs) and the advent of bidirectional chargers, EV aggregators will become a major player in the voltage regulation market.
Controlled AutoEncoders to Generate Faces from Voices
With this in perspective, we propose a framework to morph a target face in response to a given voice in a way that facial features are implicitly guided by learned voice-face correlation in this paper.
Homomorphisms to 3-manifold groups
We prove foundational results about the set of homomorphisms from a finitely generated group to the collection of all fundamental groups of compact 3-manifolds and answer questions of Reid-Wang-Zhou and Agol-Liu.
Geometric Topology Group Theory
Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
In federated optimization, heterogeneity in the clients' local datasets and computation speeds results in large variations in the number of local updates performed by each client in each communication round.
DTCA: Decision Tree-based Co-Attention Networks for Explainable Claim Verification
Simultaneously, the discovered evidence only roughly aims at the interpretability of the whole sequence of claims but insufficient to focus on the false parts of claims.
Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD
In this paper, we propose an algorithmic approach named Overlap-Local-SGD (and its momentum variant) to overlap the communication and computation so as to speedup the distributed training procedure.
