Papers
Sat 2 Mar 2024
127 papers
- AutoDefense: Multi-Agent LLM Defense against Jailbreak AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
- Chaining thoughts and LLMs to learn DNA structural biophysicsLLM reasoning → Clinical and biomedical applications
- Improving the Validity of Automatically Generated Feedback via Reinforcement LearningLLM alignment / RLHF / preference optimisation → Process reward models for reasoning +1
- NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free AttentionEfficient LLM inference and serving → KV cache optimization
- Dissecting Language Models: Machine Unlearning via Selective PruningLLM safety and security → Machine unlearning
- Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe SamplingLLM safety and security → Jailbreaking
- SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender CodeLLM agents and tool use → Multimodal and embodied agents
- On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies +1
- Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of PrivacyLLM safety and security → Machine unlearning
- TCIG: Two-Stage Controlled Image Generation with Quality Enhancement through DiffusionDiffusion models → Image generation, text-to-image and editing
- Data-free Multi-label Image Recognition via LLM-powered Prompt TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- DMoERM: Recipes of Mixture-of-Experts for Effective Reward ModelingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
- RAGged Edges: The Double-Edged Sword of Retrieval-Augmented ChatbotsRetrieval-augmented generation → Hallucination detection in RAG
- Training Unbiased Diffusion Models From Biased DatasetDiffusion models → Diffusion foundations and sampling
- BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse ResponsesSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
- LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive QuantizationEfficient LLM inference and serving → Serving systems and request scheduling
- Face Swap via Diffusion ModelDiffusion models → Image generation, text-to-image and editing
- Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation FrameworkKnowledge distillation → Graph neural network distillation
- Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)Offline RL and imitation learning from data → Imitation learning methods +1
- Coupled generator decomposition for fusion of electro- and magnetoencephalography data
- Identity information based on human magnetocardiography signals
- OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
- Knowledge-Reuse Transfer Learning Methods in Molecular and Material Science
- Beyond Inference: Performance Analysis of DNN Server Overheads for Computer Vision
- Evaluating Terrain-Dependent Performance for Martian Frost Detection in Visible Satellite Observations
- A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition
- Large Language Multimodal Models for 5-Year Chronic Disease Cohort Prediction Using EHR Data
- Analysis of Privacy Leakage in Federated Large Language Models
- A Survey on Temporal Knowledge Graph: Representation Learning and Applications
- Selective Encryption using Segmentation Mask with Chaotic Henon Map for Multidimensional Medical Images
- Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining
- An Efficient Difference-of-Convex Solver for Privacy Funnel
- Temporal Knowledge Graph Completion with Time-sensitive Relations in Hypercomplex Space
- Spatio-Temporal Field Neural Networks for Air Quality Inference
- Improve Cost Efficiency of Active Learning over Noisy Dataset
- ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation
- Mitigating the Bias in the Model for Continual Test-Time Adaptation
- LM4OPT: Unveiling the Potential of Large Language Models in Formulating Mathematical Optimization Problems
- Uniform Ck Approximation of G-Invariant and Antisymmetric Functions, Embedding Dimensions, and Polynomial Representations
- Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
- DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning
- High-Dimensional Tail Index Regression
- Less is More: Hop-Wise Graph Attention for Scalable and Generalizable Learning on Circuits
- TUMTraf V2X Cooperative Perception Dataset
- Near-optimal Per-Action Regret Bounds for Sleeping Bandits
- Image-Based Dietary Assessment: A Healthy Eating Plate Estimation System
- VNLP: Turkish NLP Package
- VBART: The Turkish LLM
- ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation
- Supplier Recommendation in Online Procurement
- Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection
- A Photonic Physically Unclonable Function's Resilience to Multiple-Valued Machine Learning Attacks
- Greed is All You Need: An Evaluation of Tokenizer Inference Methods
- Summary Paper: Use Case on Building Collaborative Safe Autonomous Systems-A Robotdog for Guiding Visually Impaired People
- Fast Low-parameter Video Activity Localization in Collaborative Learning Environments
- Optimal Integrated Task and Path Planning and Its Application to Multi-Robot Pickup and Delivery
- Can a Confident Prior Replace a Cold Posterior?
- A comprehensive cross-language framework for harmful content detection with the aid of sentiment analysis
- Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
- Single-image camera calibration with model-free distortion correction
- Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey
- Dual Graph Attention based Disentanglement Multiple Instance Learning for Brain Age Estimation
- AcME-AD: Accelerated Model Explanations for Anomaly Detection
- Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
- Augmenting Automation: Intent-Based User Instruction Classification with Machine Learning
- IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
- Active Deep Kernel Learning of Molecular Properties: Realizing Dynamic Structural Embeddings
- Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
- Benchmarking Segmentation Models with Mask-Preserved Attribute Editing
- REWIND Dataset: Privacy-preserving Speaking Status Segmentation from Multimodal Body Movement Signals in the Wild
- DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction
- Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions
- A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanations
- API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access
- Boosting Box-supervised Instance Segmentation with Pseudo Depth
- SAR-AE-SFP: SAR Imagery Adversarial Example in Real Physics domain with Target Scattering Feature Parameters
- Stochastic gradient descent for streaming linear and rectified linear systems with adversarial corruptions
- Pseudo-Label Calibration Semi-supervised Multi-Modal Entity Alignment
- The Case for Animal-Friendly AI
- Machine Translation in the Covid domain: an English-Irish case study for LoResMT 2021
- A Composite Decomposition Method for Large-Scale Global Optimization
- A Compositional Typed Semantics for Universal Dependencies
- Balancing Exploration and Exploitation in LLM using Soft RLLF for Enhanced Negation Understanding
- Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagery
- Consistent and Optimal Solution to Camera Motion Estimation
- Run-time Introspection of 2D Object Detection in Automated Driving Systems Using Learning Representations
- Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection
- DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference
- STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models
- A Bayesian Committee Machine Potential for Oxygen-containing Organic Compounds
- Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation
- A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization
- A Hybrid Model for Traffic Incident Detection based on Generative Adversarial Networks and Transformer Model
- Edge-guided Low-light Image Enhancement with Inertial Bregman Alternating Linearized Minimization
- ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies
- Neural radiance fields-based holography [Invited]
- Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data
- MPIPN: A Multi Physics-Informed PointNet for solving parametric acoustic-structure systems
- LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation
All 127
- Dynamic 3D Point Cloud Sequences as 2D Videos
- Sensitivity Analysis On Loss Landscape
- Text-guided Explorable Image Super-resolution
- ELA: Efficient Local Attention for Deep Convolutional Neural Networks
- OpenGraph: Towards Open Graph Foundation Models
- Adversarial Testing for Visual Grounding via Image-Aware Property Reduction
- MulCogBench: A Multi-modal Cognitive Benchmark Dataset for Evaluating Chinese and English Computational Language Models
- Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning
- Distilling Text Style Transfer With Self-Explanation From LLMs
- Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing
- Feature Alignment: Rethinking Efficient Active Learning via Proxy in the Context of Pre-trained Models
- Pairwise Alignment Improves Graph Domain Adaptation
- COOL: A Conjoint Perspective on Spatio-Temporal Graph Neural Network for Traffic Forecasting
- Towards Accurate Lip-to-Speech Synthesis in-the-Wild
- Beyond Night Visibility: Adaptive Multi-Scale Fusion of Infrared and Visible Images
- LAB: Large-Scale Alignment for ChatBots
- Gamma-VAE: Curvature regularized variational autoencoders for uncovering emergent low dimensional geometric structure in high dimensional data
- Extracting Usable Predictions from Quantized Networks through Uncertainty Quantification for OOD Detection
- GraphRCG: Self-Conditioned Graph Generation
- LLMCRIT: Teaching Large Language Models to Use Criteria
- FaiMA: Feature-aware In-context Learning for Multi-domain Aspect-based Sentiment Analysis
- Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers
- Neural Field Classifiers via Target Encoding and Classification Loss
- Towards Full Authorship with AI: Supporting Revision with AI-Generated Views
- Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling
- A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features
- AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks