Search Results for author:
Found 33 papers, 14 papers with code
C-TLSAN: Content-Enhanced Time-Aware Long- and Short-Term Attention Network for Personalized Recommendation
Sequential recommender systems aim to model users' evolving preferences by capturing patterns in their historical interactions.
NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution
This paper reviews the NTIRE 2025 RAW Image Restoration and Super-Resolution Challenge, highlighting the proposed solutions and results.
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
The rapid advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on model-centric scaling through increasing parameter counts from millions to hundreds of billions to drive performance gains.
NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images.
A Survey of Large Language Models in Mental Health Disorder Detection on Social Media
The detection and intervention of mental health issues represent a critical global research focus, and social media data has been recognized as an important resource for mental health research.
Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images
In this paper, we propose a novel method called Parameter Learning Attack (PLA) for tracking the copyright of LVLMs without modifying the original model.
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines.
Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
To validate the effectiveness of CFT, we construct multiple critique datasets (e. g., WebInstruct, MetaMath, NuminaMath), where GPT-4o serves as the teacher to generate critiques in the form of ([query; noisy response], critique).
Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification
While neural network-based models, such as CNN and BERT, have demonstrated remarkable performance in text classification, their effectiveness heavily relies on abundant labeled training data.
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
To address these challenges, we introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales designed to elicit CoT reasoning.
Ranked #31 on
Visual Question Answering
on MM-Vet
MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
We evaluate a wide variety of frontier vision-language models on MEGA-Bench to understand their capabilities across these dimensions.
Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities.
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
This paper introduces MMMU-Pro, a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark.
PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents
Recent advancements in Large Multimodal Models (LMMs) have leveraged extensive multimodal datasets to enhance capabilities in complex knowledge-driven tasks.
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
In the age of large-scale language models, benchmarks like the Massive Multitask Language Understanding (MMLU) have been pivotal in pushing the boundaries of what AI can achieve in language comprehension and reasoning across diverse domains.
KGLink: A column type annotation method that combines knowledge graph and pre-trained language model
By leveraging the strengths of KGLink, we successfully surmount challenges related to type granularity and valuable context issues, establishing it as a robust solution for the semantic annotation of tabular data.
MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series
To improve the transparency of LLMs, the research community has formed to open-source truly open LLMs (e. g., Pythia, Amber, OLMo), where more details (e. g., pre-training corpus and training code) are being provided.
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles.
UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence
Garment manipulation (e. g., unfolding, folding and hanging clothes) is essential for future robots to accomplish home-assistant tasks, while highly challenging due to the diversity of garment configurations, geometries and deformations.
Simulating Nighttime Visible Satellite Imagery of Tropical Cyclones Using Conditional Generative Adversarial Networks
The model was trained and validated using data from the Advanced Himawari Imager (AHI) in the daytime, achieving statistical results of SSIM = 0. 923 and Root Mean Square Error (RMSE) = 0. 0299, which significantly surpasses existing models.
ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields
This framework aims to guide the NeRF model to synthesize high-resolution novel views via single-scene internal learning rather than requiring any external high-resolution training data.
FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration
Face video restoration (FVR) is a challenging but important problem where one seeks to recover a perceptually realistic face videos from a low-quality input.
Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering (Published in Findings of EMNLP 2024)
In this study, we present a system called LLMs Augmented with Medical Textbooks (LLM-AMT) designed to enhance the proficiency of LLMs in specialized domains.
YZR-net : Self-supervised Hidden representations Invariant to Transformations for profanity detection
Some miscreants use this framework to send profane messages which can have a negative impact on other students as well as the teacher of the class.
Looking For A Match: Self-supervised Clustering For Automatic Doubt Matching In e-learning Platforms
Results highlighted that, custom BYOL improves the top-1 matching accuracy by approximately 6\% and 5\% as compared to both BYOL and supervised learning instances, respectively.
Mitosis domain generalization in histopathology images -- The MIDOG challenge
The goal of the MICCAI MIDOG 2021 challenge has been to propose and evaluate methods that counter this domain shift and derive scanner-agnostic mitosis detection algorithms.
A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems
We conduct further analysis on the impact of both observations and actions: on the observation end, we examine the robustness of graph-based policy on two typical data acquisition errors in power systems, namely sensor communication failure and measurement misalignment.
Soft Actor-Critic With Integer Actions
Reinforcement learning is well-studied under discrete actions.
PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems
We introduce PowerGym, an open-source reinforcement learning environment for Volt-Var control in power distribution systems.
Detecting Mitosis against Domain Shift using a Fused Detector and Deep Ensemble Classification Model for MIDOG Challenge
Mitotic figure count is an important marker of tumor proliferation and has been shown to be associated with patients' prognosis.
