Search Results for author:
Found 44 papers, 30 papers with code
Short Text Topic Modeling with Topic Distribution Quantization and Negative Sampling Decoder
Topic models have been prevailing for many years on discovering latent semantics while modeling long documents.
Detecting Harmful Memes with Decoupled Understanding and Guided CoT Reasoning
Building on these textual descriptions, we further incorporate targeted, interpretable human-crafted guidelines to guide models' reasoning under zero-shot CoT prompting.
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
We evaluate two token-reduction strategies: token pruning and token merging.
SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation
Process Reward Models (PRMs) have demonstrated promising results in mathematical reasoning, but existing process annotation approaches, whether through human annotations or Monte Carlo simulations, remain computationally expensive.
Sailing AI by the Stars: A Survey of Learning from Rewards in Post-Training and Test-Time Scaling of Large Language Models
In this survey, we present a comprehensive overview of the paradigm of learning from rewards.
Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation
To address these challenges, in this paper, we propose a novel framework for aspect-based summarization: Self-Aspect Retrieval Enhanced Summary Generation.
HyperGraphRAG: Retrieval-Augmented Generation with Hypergraph-Structured Knowledge Representation
To retrieve and generate over hypergraphs, we introduce a complete pipeline with a hypergraph construction method, a hypergraph retrieval strategy, and a hypergraph-guided generation mechanism.
Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
Direct Preference Optimization (DPO) often struggles with long-chain mathematical reasoning.
CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base
Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, but they remain susceptible to hallucination, particularly object hallucination where non-existent objects or incorrect attributes are fabricated in generated descriptions.
Hierarchical Graph Topic Modeling with Topic Tree-based Transformer
We thus propose a Hierarchical Graph Topic Modeling Transformer to integrate both topic hierarchy within documents and graph hierarchy across documents into a unified Transformer.
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
Moreover, it employs MCTS, a heuristic search method driven by policy and reward models, to balance agentic exploration's performance and search space.
Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation
Previous research on multimodal entity linking (MEL) has primarily employed contrastive learning as the primary objective.
AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge
Data contamination hinders fair LLM evaluation by introducing test data into newer models' training sets.
RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios
This paper introduces RuleArena, a novel and challenging benchmark designed to evaluate the ability of large language models (LLMs) to follow complex, real-world rules in reasoning.
Multi-Scale Contrastive Learning for Video Temporal Grounding
To resolve this problem, we propose a contrastive learning framework to capture salient semantics among video moments.
Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation
To overcome this limitation, we introduce a contrastive representation learning framework that focuses on motion pattern for temporal scene graph generation.
Curriculum Demonstration Selection for In-Context Learning
Large Language Models (LLMs) have shown strong in-context learning (ICL) abilities with a few demonstrations.
Are LLMs Good Zero-Shot Fallacy Classifiers?
To elicit fallacy-related knowledge and reasoning abilities of LLMs, we propose diverse single-round and multi-round prompting schemes, applying different task-specific instructions such as extraction, summarization, and Chain-of-Thought reasoning.
Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
Then, this teacher model guides the large-scale poisoned student model in unlearning the backdoor, leveraging PEFT.
COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement
Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally during the generation process.
Weak-to-Strong Backdoor Attack for Large Language Models
Despite being widely applied due to their exceptional capabilities, Large Language Models (LLMs) have been proven to be vulnerable to backdoor attacks.
Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels
We iteratively prompt LLMs to annotate unlabeled data and retain high-quality labels by filtering.
MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
To address these problems, we propose MAMA, a new approach to learning video-language representations by utilizing a contrastive objective with a subtractive angular margin to regularize cross-modal representations in their effort to reach perfect similarity.
A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings.
Encoding and Controlling Global Semantics for Long-form Video Question Answering
Seeking answers effectively for long videos is essential to build video question answering (videoQA) systems.
FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model
We further propose a novel Embedding Transport Plan (ETP) method.
Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
However, existing models suffer from repetitive topic and unassociated topic issues, failing to reveal the evolution and hindering further applications.
KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning
Previous work on multimodal sentence embedding has proposed multimodal contrastive learning and achieved promising results.
AKEW: Assessing Knowledge Editing in the Wild
Knowledge editing injects knowledge updates into language models to keep them correct and up-to-date.
Topic Modeling as Multi-Objective Contrastive Optimization
Secondly, we explicitly cast contrastive topic modeling as a gradient-based multi-objective optimization problem, with the goal of achieving a Pareto stationary solution that balances the trade-off between the ELBO and the contrastive objective.
A Survey on Neural Topic Models: Methods, Applications, and Challenges
In this paper, we present a comprehensive survey on neural topic models concerning methods, applications, and challenges.
READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization.
DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
Temporal Language Grounding seeks to localize video moments that semantically correspond to a natural language query.
Towards the TopMost: A Topic Modeling System Toolkit
Topic models have a rich history with various applications and have recently been reinvigorated by neural topic modeling.
Effective Neural Topic Modeling with Embedding Clustering Regularization
Topic models have been prevalent for decades with various applications.
Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction
Multimodal Review Helpfulness Prediction (MRHP) aims to rank product reviews based on predicted helpfulness scores and has been widely applied in e-commerce via presenting customers with useful reviews.
Fact-Checking Complex Claims with Program-Guided Reasoning
Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning.
Zero-Shot Text Classification via Self-Supervised Tuning
In this work, we propose a new paradigm based on self-supervised learning to solve zero-shot text classification tasks by tuning the language models with unlabeled data, called self-supervised tuning.
InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
Instead of the direct alignment in previous work, we propose a topic alignment with mutual information method.
Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning
To overcome the data sparsity issue in short text topic modeling, existing methods commonly rely on data augmentation or the data characteristic of short texts to introduce more word co-occurrence information.
Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions
To overcome the aforementioned issues, we propose Multimodal Contrastive Learning for Multimodal Review Helpfulness Prediction (MRHP) problem, concentrating on mutual information between input modalities to explicitly elaborate cross-modal relations.
Vision-and-Language Pretraining
Moreover, a list of training datasets and downstream tasks is supplied to further polish the perspective into V\&L pretraining.
