Papers
Sat 6 Jul 2024
116 papers
- BadCLM: Backdoor Attack in Clinical Language Models for Electronic Health RecordsLLM safety and security → Safety alignment, refusal and guardrails
- FlowLearn: Evaluating Large Vision-Language Models on Flowchart UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
- A Novel Bifurcation Method for Observation Perturbation Attacks on Reinforcement Learning Agents: Load Altering Attacks on a Cyber Physical Power SystemDeep reinforcement learning methods → RL for energy, networks and operations
- Lucy: Think and Reason to Solve Text-to-SQLLLM reasoning → Knowledge- and tool-augmented reasoning
- Are LLMs Correctly Integrated into Software Systems?Retrieval-augmented generation → RAG for code
- RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
- Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine UnlearningLLM safety and security → Machine unlearning
- Test-time Contrastive Concepts for Open-world Semantic Segmentation with Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Slice-Consistent 3D Volumetric Brain CT-to-MRI Translation with 2D Brownian Bridge Diffusion ModelDiffusion models → Medical imaging and segmentation
- Progress or Regress? Self-Improvement Reversal in Post-trainingLLM reasoning → Reinforcement learning for reasoning +1
- Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-TuningLLM agents and tool use → Tool learning and function calling
- LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual ContextsLLM reasoning → Multimodal reasoning +1
- Granular Privacy Control for Geolocation with Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- FreeCompose: Generic Zero-Shot Image Composition with Diffusion PriorDiffusion models → Image generation, text-to-image and editing
- FOSP: Fine-tuning Offline Safe Policy through World ModelsWorld models → Latent dynamics models and model-based RL +2
- SAM-Med3D-MoE: Towards a Non-Forgetting Segment Anything Model via Mixture of Experts for 3D Medical Image SegmentationMixture-of-experts → Medical and biomedical MoE
- RAMO: Retrieval-Augmented Generation for Enhancing MOOCs RecommendationsRetrieval-augmented generation → RAG for recommendation
- OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
- Safe Generative Chats in a WhatsApp Intelligent Tutoring SystemLLM safety and security → Safety alignment, refusal and guardrails
- MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
- AI Safety in Generative AI Large Language Models: A Survey
- Data Poisoning Attacks in Intelligent Transportation Systems: A Survey
- Large language models are good medical coders, if provided with tools
- Applicability of Large Language Models and Generative Models for Legal Case Judgement Summarization
- Dy-mer: An Explainable DNA Sequence Representation Scheme using Dictionary Learning
- An Automated Approach to Collecting and Labeling Time Series Data for Event Detection Using Elastic Node Hardware
- Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT
- High-Quality and Full Bandwidth Seismic Signal Synthesis using Operational GANs
- Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation
- Fuzzy Recurrent Stochastic Configuration Networks for Industrial Data Analytics
- Communication and Control Co-Design in 6G: Sequential Decision-Making with LLMs
- Quantum Machine Learning with Application to Progressive Supranuclear Palsy Network Classification
- Helios: An extremely low power event-based gesture recognition for always-on smart eyewear
- Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing
- A Generalized Transformer-based Radio Link Failure Prediction Framework in 5G RANs
- LLMCloudHunter: Harnessing LLMs for Automated Extraction of Detection Rules from Cloud-Based CTI
- CBM: Curriculum by Masking
- Enhancing Language Learning through Technology: Introducing a New English-Azerbaijani (Arabic Script) Parallel Corpus
- Synthetic Data Aided Federated Learning Using Foundation Models
- A Domain Adaptation Model for Carotid Ultrasound: Image Harmonization, Noise Reduction, and Impact on Cardiovascular Risk Markers
- Identifying Intensity of the Structure and Content in Tweets and the Discriminative Power of Attributes in Context with Referential Translation Machines
- On high-dimensional modifications of the nearest neighbor classifier
- Impact of Network Topology on Byzantine Resilience in Decentralized Federated Learning
- Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?
- SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention
- A Joint Approach to Local Updating and Gradient Compression for Efficient Asynchronous Federated Learning
- Open-Event Procedure Planning in Instructional Videos
- SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding
- Automatic Prediction of the Performance of Every Parser
- The Role of Depth, Width, and Tree Size in Expressiveness of Deep Forest
- DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition
- Towards Auto-Building of Embedded FPGA-based Soft Sensors for Wastewater Flow Estimation
- Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference
- FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning
- Exploring Sound Change Over Time: A Review of Computational and Human Perception
- Leveraging Task-Specific Knowledge from LLM for Semi-Supervised 3D Medical Image Segmentation
- Linear Attention Based Deep Nonlocal Means Filtering for Multiplicative Noise Removal
- DMTG: One-Shot Differentiable Multi-Task Grouping
- Form Forge: Latent Space Exploration of Architectural Forms via Explicit Latent Variable Manipulation
- Advancing Algorithmic Approaches to Probabilistic Argumentation under the Constellation Approach
- Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning
- BrainMetDetect: Predicting Primary Tumor from Brain Metastasis MRI Data Using Radiomic Features and Machine Learning Algorithms
- Sparse identification of quasipotentials via a combined data-driven method
- MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning
- Robust Skin Color Driven Privacy Preserving Face Recognition via Function Secret Sharing
- Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruning
- Enhance the Robustness of Text-Centric Multimodal Alignments
- SurgicalGaussian: Deformable 3D Gaussians for High-Fidelity Surgical Scene Reconstruction
- A Principled Framework for Evaluating on Typologically Diverse Languages
- Incremental Multiview Point Cloud Registration
- How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions
- PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference
- T-CorresNet: Template Guided 3D Point Cloud Completion with Correspondence Pooling Query Generation Strategy
- BlessemFlood21: Advancing Flood Analysis with a High-Resolution Georeferenced Dataset for Humanitarian Aid Support
- Recent Advancements and Challenges of Turkic Central Asian Language Processing
- Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching
- LoRA-GA: Low-Rank Adaptation with Gradient Approximation
- Rethinking the Effectiveness of Graph Classification Datasets in Benchmarks for Assessing GNNs
- The Solution for the 5th GCAIAC Zero-shot Referring Expression Comprehension Challenge
- The Solution for the sequential task continual learning track of the 2nd Greater Bay Area International Algorithm Competition
- The Solution for Language-Enhanced Image New Category Discovery
- Scalable Variational Causal Discovery Unconstrained by Acyclicity
- The Solution for the AIGC Inference Performance Optimization Competition
- Conditional Semi-Supervised Data Augmentation for Spam Message Detection with Low Resource Data
- The Reachability Problem for Neural-Network Control Systems
- Calorie Burn Estimation in Community Parks Through DLICP: A Mathematical Modelling Approach
- Combining Neuroevolution with the Search for Novelty to Improve the Generation of Test Inputs for Games
- TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs
- Enabling Causal Discovery in Post-Nonlinear Models with Normalizing Flows
- Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments
- Idiographic Personality Gaussian Process for Psychological Assessment
- EVA-Score: Evaluating Abstractive Long-form Summarization on Informativeness through Extraction and Validation
- A Layer-Anchoring Strategy for Enhancing Cross-Lingual Speech Emotion Recognition
- Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression
- ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters
- Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training
- Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models
- Asynchronous Multimodal Video Sequence Fusion via Learning Modality-Exclusive and -Agnostic Representations
- Effective-LDAM: An Effective Loss Function To Mitigate Data Imbalance for Robust Chest X-Ray Disease Classification
- Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients
All 116
- Zero-shot Object Counting with Good Exemplars
- On Differentially Private U Statistics
- Quantizing YOLOv7: A Comprehensive Study
- Resource Constrained U-Net for Extraction of Retinal Vascular Trees
- Balance of Number of Embedding and their Dimensions in Vector Quantization
- CLIPVQA:Video Quality Assessment via CLIP
- JDT3D: Addressing the Gaps in LiDAR-Based Tracking-by-Attention
- Aortic root landmark localization with optimal transport loss for heatmap regression
- qlty: handling large tensors in scientific imaging
- Completed Feature Disentanglement Learning for Multimodal MRIs Analysis
- Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation
- NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task
- SID: Stereo Image Dataset for Autonomous Driving in Adverse Conditions
- Regret Optimality of Sample Average Approximation for Data-Driven Newsvendor Problems: A General Optimization Perspective
- Algorithmic Language Models with Neurally Compiled Libraries
- Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online Learning