Search Results for author:
Found 30 papers, 20 papers with code
UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation
Multimodal Large Language Models (MLLMs) have emerged to tackle the challenges of Visual Question Answering (VQA), sparking a new research focus on conducting objective evaluations of these models.
Frame-wise Conditioning Adaptation for Fine-Tuning Diffusion Models in Text-to-Video Prediction
In this work, we propose an adaptation-based strategy we label Frame-wise Conditioning Adaptation (FCA).
Superficial Self-Improved Reasoners Benefit from Model Merging
As scaled language models (LMs) approach human-level reasoning capabilities, self-improvement emerges as a solution to synthesizing high-quality data corpus.
Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
While some prior works have explored this issue in the context of LLMs, it presents a unique challenge for MLLMs due to the entangled nature of knowledge across modalities, making comprehensive unlearning more difficult.
Can Large Language Models Understand Preferences in Personalized Recommendation?
To address this, we introduce PerRecBench, disassociating the evaluation from these two factors and assessing recommendation techniques on capturing the personal preferences in a grouped ranking manner.
CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP
Machine unlearning (MU) has gained significant attention as a means to remove specific data from trained models without requiring a full retraining process.
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidential and private data, raising legal and ethical concerns.
OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection
Further, to infer the keypoint location of unseen texts, we add the auxiliary keypoints and texts interpolated from visual and textual domains into training, which improves the spatial reasoning of our model and significantly enhances zero-shot novel keypoint detection.
Machine Unlearning in Generative AI: A Survey
We offer a comprehensive survey on many things about MU in Generative AI, such as a new problem formulation, evaluation methods, and a structured discussion on the advantages and limitations of different kinds of MU techniques.
DiffStega: Towards Universal Training-Free Coverless Image Steganography with Diffusion Models
Traditional image steganography focuses on concealing one image within another, aiming to avoid steganalysis by unauthorized entities.
Avoiding Copyright Infringement via Large Language Model Unlearning
In real-world scenarios, model owners need to continuously address copyright infringement as new requests for content removal emerge at different time points.
Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts
Personalized large language models (LLMs) aim to tailor interactions, content, and recommendations to individual user preferences.
Graph Learning for Parameter Prediction of Quantum Approximate Optimization Algorithm
In recent years, quantum computing has emerged as a transformative force in the field of combinatorial optimization, offering novel approaches to tackling complex problems that have long challenged classical computational methods.
Towards Safer Large Language Models through Machine Unlearning
To address this gap, we introduce Selective Knowledge negation Unlearning (SKU), a novel unlearning framework for LLMs, designed to eliminate harmful knowledge while preserving utility on normal prompts.
Can we Soft Prompt LLMs for Graph Learning Tasks?
Graph plays an important role in representing complex relationships in real-world applications such as social networks, biological data and citation networks.
UGMAE: A Unified Framework for Graph Masked Autoencoders
In light of this, we propose UGMAE, a unified framework for graph masked autoencoders to address these issues from the perspectives of adaptivity, integrity, complementarity, and consistency.
Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning
OPPU integrates parametric user knowledge in the personal PEFT parameters with non-parametric knowledge from retrieval and profiles, adapting LLMs to user behavior shifts.
Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
Exploring the full spectrum of trade-offs between privacy, model utility, and runtime efficiency is critical for practical unlearning scenarios.
A Generalized Physical-knowledge-guided Dynamic Model for Underwater Image Enhancement
To tackle these challenges, we design a Generalized Underwater image enhancement method via a Physical-knowledge-guided Dynamic Model (short for GUPDM), consisting of three parts: Atmosphere-based Dynamic Structure (ADS), Transmission-guided Dynamic Structure (TDS), and Prior-based Multi-scale Structure (PMS).
Histogram-guided Video Colorization Structure with Spatial-Temporal Connection
Video colorization, aiming at obtaining colorful and plausible results from grayish frames, has aroused a lot of interest recently.
All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation
Given a pair of augmented views, our approach regularizes the activation intensities between a pair of augmented views, while also ensuring that the affinity across regions within each view remains consistent.
Ranked #16 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder
An alternative approach is to allow interactions between the query and every possible candidate, i. e., reference-text-candidate triplets, and pick the best from the entire set.
Ranked #4 on
Image Retrieval
on Fashion IQ
An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
The Segment Anything Model (SAM) has demonstrated exceptional performance and versatility, making it a promising tool for various related tasks.
Ranked #3 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
(using extra training data)
Bi-directional Training for Composed Image Retrieval via Text Prompt Learning
Composed image retrieval searches for a target image based on a multi-modal user query comprised of a reference image and modification text describing the desired changes.
Ranked #8 on
Image Retrieval
on Fashion IQ
Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning
Based on this observation, we propose a new learning strategy named False Negative Aware Contrastive (FNAC) to mitigate the problem of misleading the training with such false negative samples.
GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation
To bridge their gap, a Class Activation Map (CAM) is usually generated to provide pixel level pseudo labels.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
We demonstrate that with a relatively simple architecture, CIRPLANT outperforms existing methods on open-domain images, while matching state-of-the-art accuracy on the existing narrow datasets, such as fashion.
Ranked #16 on
Image Retrieval
on CIRR
Arterial incident duration prediction using a bi-level framework of extreme gradient-tree boosting
Predicting traffic incident duration is a major challenge for many traffic centres around the world.
KnowYourNyms? A Game of Semantic Relationships
Semantic relation knowledge is crucial for natural language understanding.
