mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 19 Feb 2024

338 papers

  1. Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  2. Purifying Large Language Models by Ensembling a Small Language ModelLLM safety and security → Machine unlearning
  3. Text Diffusion with Reinforced ConditioningDiffusion models → Discrete and text diffusion
  4. RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical ReasoningLLM reasoning → Clinical and biomedical applications
  5. Offline Multi-task Transfer RL with Representational PenalizationOffline RL and imitation learning from data → Offline RL algorithms
  6. Multilinear Mixture of Experts: Scalable Expert Specialization through FactorizationMixture-of-experts → Vision mixture-of-experts
  7. ADEPT: Hierarchical Bayes Approach to Personalized Federated Unsupervised LearningDiffusion models → Robustness, privacy and adversarial aspects
  8. The Edge-of-Reach Problem in Offline Model-Based Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  9. Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data SelectionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  10. In value-based deep reinforcement learning, a pruned network is a good networkDeep reinforcement learning methods → Deep RL algorithms and representations
  11. The Revolution of Multimodal Large Language Models: A SurveyMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  12. Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMsLLM reasoning → Knowledge- and tool-augmented reasoning
  13. On the Semantic Latent Space of Diffusion-Based Text-to-Speech ModelsDiffusion models → Audio, speech and music
  14. FiT: Flexible Vision Transformer for Diffusion ModelDiffusion models → Diffusion foundations and sampling
  15. Sequoia: Scalable, Robust, and Hardware-aware Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  16. A synthetic data approach for domain generalization of NLI modelsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  17. A Critical Evaluation of AI Feedback for Aligning Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  18. Graph-Based Retriever Captures the Long Tail of Biomedical KnowledgeRetrieval-augmented generation → Medical and biomedical RAG
  19. GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic EvaluationsLLM reasoning → Reasoning for agents, planning and code
  20. Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  21. Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  22. Query-Based Adversarial Prompt GenerationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  23. Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  24. EVOR: Evolving Retrieval for Code GenerationRetrieval-augmented generation → RAG for code
  25. DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  26. Refining Minimax Regret for Unsupervised Environment DesignDeep reinforcement learning methods → Deep RL algorithms and representations
  27. Plato: Plan to Efficiently Decode for Large Language Model InferenceEfficient LLM inference and serving → Speculative decoding
  28. WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the EnvironmentWorld models → World models for language agents +1
  29. On the Byzantine-Resilience of Distillation-Based Federated LearningKnowledge distillation → Federated, robust and private distillation
  30. Analysis of Levenshtein Transformer's Decoder and Its VariantsEfficient LLM inference and serving → Speculative decoding
  31. Synthetic location trajectory generation using categorical diffusion modelsDiffusion models → Diffusion and flow policies for robotics
  32. AnyGPT: Unified Multimodal LLM with Discrete Sequence ModelingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  33. Reformatted AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  34. Polarization of Autonomous Generative AI Agents Under Echo ChambersLLM agents and tool use → Social simulation and multi-agent debate
  35. Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich LanguagesKnowledge distillation → Knowledge distillation for LLMs
  36. Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPTMechanistic interpretability → Circuits and mechanistic analysis
  37. Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their InterpretationsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs +1
  38. Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context FusionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  39. Pan-Mamba: Effective pan-sharpening with State Space ModelState-space sequence models (S4, Mamba) → Vision Mamba backbones
  40. Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled MembershipsLLM safety and security → Membership inference attacks
  41. ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart ReasoningLLM reasoning → Multimodal reasoning +1
  42. Revisiting Data Augmentation in Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  43. Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-TuningRetrieval-augmented generation → Generation and context integration
  44. BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting EvidenceRetrieval-augmented generation → RAG robustness and adaptive retrieval
  45. IRR: Image Review Ranking Framework for Evaluating Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  46. Zero-Shot Video Translation via Token WarpingDiffusion models → Video generation
  47. Do Large Language Models Understand Logic or Just Mimick Context?LLM reasoning → Reasoning benchmarks and evaluation
  48. Can LLMs Compute with Reasons?LLM reasoning → Reasoning benchmarks and evaluation
  49. LVCHAT: Facilitating Long Video ComprehensionMultimodal LLMs / vision-language models → Video understanding with MLLMs
  50. Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  51. Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  52. When Do Off-Policy and On-Policy Policy Gradient Methods Align?Deep reinforcement learning methods → RL theory and sample complexity
  53. Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMsKnowledge distillation → Knowledge distillation for LLMs
  54. Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency SpaceLLM safety and security → Backdoor and data poisoning attacks
  55. Distilling Large Language Models for Text-Attributed Graph LearningKnowledge distillation → Graph neural network distillation
  56. An Index Policy Based on Sarsa and Q-learning for Heterogeneous Smart Target TrackingDeep reinforcement learning methods → RL for robot navigation and UAV control
  57. Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  58. Remember This Event That Year? Assessing Temporal Information and Reasoning in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  59. Privacy-Preserving Low-Rank Adaptation against Membership Inference Attacks for Latent Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  60. CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI AutomationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  61. DiLightNet: Fine-grained Lighting Control for Diffusion-based Image GenerationDiffusion models → 3D, point cloud and scene generation
  62. Cofca: A Step-Wise Counterfactual Multi-hop QA benchmarkLLM reasoning → Knowledge- and tool-augmented reasoning
  63. Spatio-Temporal Few-Shot Learning via Diffusive Neural Network GenerationDiffusion models → 3D, point cloud and scene generation
  64. Unraveling Complex Data Diversity in Underwater Acoustic Target Recognition through Convolution-based Mixture of ExpertsMixture-of-experts → Vision mixture-of-experts
  65. Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt DistillationLLM reasoning → Reinforcement learning for reasoning +2
  66. DiLA: Enhancing LLM Tool Learning with Differential Logic LayerLLM reasoning → Reasoning benchmarks and evaluation +1
  67. Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  68. FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  69. Revisiting Knowledge Distillation for Autoregressive Language ModelsKnowledge distillation → Knowledge distillation for LLMs
  70. Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQDeep reinforcement learning methods → RL theory and sample complexity
  71. How Interpretable are Reasoning Explanations from Prompting Large Language Models?LLM reasoning → Prompting and chain-of-thought reasoning
  72. ComFusion: Personalized Subject Generation in Multiple Specific Scenes From Single ImageDiffusion models → Image generation, text-to-image and editing
  73. UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  74. Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret MinimizationDeep reinforcement learning methods → RL for games and combinatorial optimization
  75. Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in ConversationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  76. A novel framework for adaptive stress testing of autonomous vehicles in multi-lane roadsEnd-to-end autonomous driving → Adversarial scenarios and safety testing +1
  77. Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct DecodingEfficient LLM inference and serving → Speculative decoding
  78. LLM as Prompter: Low-resource Inductive Reasoning on Arbitrary Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
  79. Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian SamplingDeep reinforcement learning methods → RL theory and sample complexity
  80. Decentralized Multi-Robot Navigation for Autonomous Surface Vehicles with Distributional Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  81. Unveiling the Magic: Investigating Attention Distillation in Retrieval-augmented GenerationRetrieval-augmented generation → Generation and context integration
  82. SInViG: A Self-Evolving Interactive Visual Agent for Human-Robot InteractionLLM agents and tool use → Multimodal and embodied agents
  83. What Evidence Do Language Models Find Convincing?Retrieval-augmented generation → Medical and biomedical RAG
  84. Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA ConversationsLLM reasoning → Prompting and chain-of-thought reasoning
  85. Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image SegmentationDeep reinforcement learning methods → RL training of language and agent models
  86. ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMsLLM safety and security → Vision-language and text-to-image safety
  87. Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task ArithmeticLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  88. A real-time Artificial Intelligence system for learning Sign Language
  89. AI Sustainability in Practice Part Two: Sustainability Throughout the AI Workflow
  90. AI Ethics and Governance in Practice: An Introduction
  91. Large Language Model for Mental Health: A Systematic Review
  92. AI Fairness in Practice
  93. AI Sustainability in Practice Part One: Foundations for Sustainable AI Projects
  94. Multimodal Fusion of EHR in Structures and Semantics: Integrating Clinical Records and Notes with Hypergraph and LLM
  95. Applying News and Media Sentiment Analysis for Generating Forex Trading Signals
  96. Revealing the Relationship Between Publication Bias and Chemical Reactivity with Contrastive Learning
  97. Detecting misinformation through Framing Theory: the Frame Element-based Model
  98. Graph Pruning for Enumeration of Minimal Unsatisfiable Subsets
  99. Asynchronous and Segmented Bidirectional Encoding for NMT
  100. Deep learning-driven scheduling algorithm for a single machine problem minimizing the total tardiness
All 338
  1. Stick to your Role! Stability of Personal Values Expressed in Large Language Models
  2. The New Era of Dynamic Pricing: Synergizing Supervised Learning and Quadratic Programming
  3. RFBES at SemEval-2024 Task 8: Investigating Syntactic and Semantic Features for Distinguishing AI-Generated and Human-Written Texts
  4. A Conflict-Aware Optimal Goal Assignment Algorithm for Multi-Robot Systems
  5. DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models
  6. Grounding from an AI and Cognitive Science Lens
  7. Training Table Question Answering via SQL Query Decomposition
  8. Manipulating hidden-Markov-model inferences by corrupting batch data
  9. Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures
  10. Structure Guided Large Language Model for SQL Generation
  11. What is a word?
  12. Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
  13. Truncated Polynomial Expansion-Based Detection in Massive MIMO: A Model-Driven Deep Learning Approach
  14. Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation
  15. Evolving AI Collectives to Enhance Human Diversity and Enable Self-Regulation
  16. FairProof : Confidential and Certifiable Fairness for Neural Networks
  17. GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
  18. Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models
  19. Dynamic Pricing and Learning with Long-term Reference Effects
  20. CausalGym: Benchmarking causal interpretability methods on linguistic tasks
  21. Evaluation of Country Dietary Habits Using Machine Learning Techniques in Relation to Deaths from COVID-19
  22. Creating a Fine Grained Entity Type Taxonomy Using LLMs
  23. IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction
  24. Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning
  25. Landmark-based Localization using Stereo Vision and Deep Learning in GPS-Denied Battlefield Environment
  26. TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness
  27. Impact of data for forecasting on performance of model predictive control in buildings with smart energy storage
  28. A Machine Learning Ensemble Model for the Detection of Cyberbullying
  29. Designing High-Performing Networks for Multi-Scale Computer Vision
  30. Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
  31. Scalable Human-Machine Point Cloud Compression
  32. Improving Deep Generative Models on Many-To-One Image-to-Image Translation
  33. Parallel Structures in Pre-training Data Yield In-Context Learning
  34. LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks
  35. An evaluation of Deep Learning based stereo dense matching dataset shift from aerial images and a large scale stereo dataset
  36. Dynamics Based Neural Encoding with Inter-Intra Region Connectivity
  37. Gaussian Process Neural Additive Models
  38. Induced Model Matching: Restricted Models Help Train Full-Featured Models
  39. SDEs for Minimax Optimization
  40. PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling
  41. Integrating kNN with Foundation Models for Adaptable and Privacy-Aware Image Classification
  42. Automated Security Response through Online Learning with Adaptive Conjectures
  43. Feudal Networks for Visual Navigation
  44. Towards Cross-Domain Continual Learning
  45. Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!
  46. Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?
  47. SECP: A Speech Enhancement-Based Curation Pipeline For Scalable Acquisition Of Clean Speech
  48. Diffeomorphism Neural Operator for various domains and parameters of partial differential equations
  49. Neuro-mimetic Task-free Unsupervised Online Learning with Continual Self-Organizing Maps
  50. DBNets: A publicly available deep learning tool to measure the masses of young planets in dusty protoplanetary discs
  51. Emulating the interstellar medium chemistry with neural operators
  52. Understanding Fine-grained Distortions in Reports of Scientific Findings
  53. Attacks on Node Attributes in Graph Neural Networks
  54. Simulacra as Conscious Exotica
  55. EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
  56. Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures
  57. Predicting trucking accidents with truck drivers 'safety climate perception across companies: A transfer learning approach
  58. Aligning Individual and Collective Objectives in Multi-Agent Cooperation
  59. Vehicle-group-based Crash Risk Prediction and Interpretation on Highways
  60. Dynamic and Super-Personalized Media Ecosystem Driven by Generative AI: Unpredictable Plays Never Repeating The Same
  61. Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks
  62. Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis
  63. LTL learning on GPUs
  64. HunFlair2 in a cross-corpus evaluation of biomedical named entity recognition and normalization tools
  65. AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies
  66. Short-Period Variables in TESS Full-Frame Image Light Curves Identified via Convolutional Neural Networks
  67. Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators
  68. Emergent Word Order Universals from Cognitively-Motivated Language Models
  69. Nonlinear Discrete-Time Observers with Physics-Informed Neural Networks
  70. LoRA+: Efficient Low Rank Adaptation of Large Models
  71. An Adversarial Approach to Evaluating the Robustness of Event Identification Models
  72. Image Super-resolution Inspired Electron Density Prediction
  73. Triple-Encoders: Representations That Fire Together, Wire Together
  74. Generating Survival Interpretable Trajectories and Data
  75. PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents
  76. Landmark Stereo Dataset for Landmark Recognition and Moving Node Localization in a Non-GPS Battlefield Environment
  77. Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness
  78. TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs
  79. Multi-View Conformal Learning for Heterogeneous Sensor Fusion
  80. UncertaintyTrack: Exploiting Detection and Localization Uncertainty in Multi-Object Tracking
  81. Asymptotic Gaussian Fluctuations of Eigenvectors in Spectral Clustering
  82. Is Open-Source There Yet? A Comparative Study on Commercial and Open-Source LLMs in Their Ability to Label Chest X-Ray Reports
  83. Regularization by denoising: Bayesian model and Langevin-within-split Gibbs sampling
  84. KARL: Knowledge-Aware Retrieval and Representations aid Retention and Learning in Students
  85. Ontology Enhanced Claim Detection
  86. Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks
  87. Secure Federated Learning Across Heterogeneous Cloud and High-Performance Computing Resources -- A Case Study on Federated Fine-tuning of LLaMA 2
  88. Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
  89. High-quality Data-to-Text Generation for Severely Under-Resourced Languages with Out-of-the-box Large Language Models
  90. Uncertainty quantification in fine-tuned LLMs using LoRA ensembles
  91. Towards a tailored mixed-precision sub-8-bit quantization scheme for Gated Recurrent Units using Genetic Algorithms
  92. NEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms
  93. Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
  94. Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition
  95. Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench Benchmark
  96. Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis
  97. BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
  98. MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction
  99. Learning to Defer in Congested Systems: The AI-Human Interplay
  100. The Fundamental Limits of Least-Privilege Learning
  101. Task-Oriented Dialogue with In-Context Learning
  102. Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers
  103. Kernel KMeans clustering splits for end-to-end unsupervised decision trees
  104. Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations
  105. Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability
  106. CovRL: Fuzzing JavaScript Engines with Coverage-Guided Reinforcement Learning for LLM-based Mutation
  107. Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting
  108. Copyleft for Alleviating AIGC Copyright Dilemma: What-if Analysis, Public Perception and Implications
  109. Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach
  110. A Chinese Dataset for Evaluating the Safeguards in Large Language Models
  111. Towards AI-Based Precision Oncology: A Machine Learning Framework for Personalized Counterfactual Treatment Suggestions based on Multi-Omics Data
  112. Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training
  113. Colorizing Monochromatic Radiance Fields
  114. MultiFIX: An XAI-friendly feature inducing approach to building models from multimodal data
  115. Examining Monitoring System: Detecting Abnormal Behavior In Online Examinations
  116. Learning Discretized Bayesian Networks with GOMEA
  117. Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
  118. Endowing Pre-trained Graph Models with Provable Fairness
  119. Transformer-based Causal Language Models Perform Clustering
  120. Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One
  121. MLFEF: Machine Learning Fusion Model with Empirical Formula to Explore the Momentum in Competitive Sports
  122. Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models
  123. Enabling Weak LLMs to Judge Response Reliability via Meta Ranking
  124. Federated Bayesian Network Ensembles
  125. Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
  126. Molecule Generation and Optimization for Efficient Fragrance Creation
  127. SSTKG: Simple Spatio-Temporal Knowledge Graph for Intepretable and Versatile Dynamic Information Embedding
  128. 3D Vascular Segmentation Supervised by 2D Annotation of Maximum Intensity Projection
  129. Sparse, Efficient and Explainable Data Attribution with DualXDA
  130. A Spatiotemporal Illumination Model for 3D Image Fusion in Optical Coherence Tomography
  131. Is It a Free Lunch for Removing Outliers during Pretraining?
  132. Groot: Adversarial Testing for Generative Text-to-Image Models with Tree-based Semantic Transformation
  133. Towards Explainable LiDAR Point Cloud Semantic Segmentation via Gradient Based Target Localization
  134. Major TOM: Expandable Datasets for Earth Observation
  135. HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
  136. Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overview
  137. EmoBench: Evaluating the Emotional Intelligence of Large Language Models
  138. Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks
  139. WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More
  140. Causal Equal Protection as Algorithmic Fairness
  141. All Language Models Large and Small
  142. Are LLM-based Evaluators Confusing NLG Quality Criteria?
  143. Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs
  144. Citation Amnesia: On The Recency Bias of NLP and Other Academic Fields
  145. A Lightweight Parallel Framework for Blind Image Quality Assessment
  146. Linear bandits with polylogarithmic minimax regret
  147. Surround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challenges
  148. Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations
  149. Language Model Adaptation to Specialized Domains through Selective Masking based on Genre and Topical Characteristics
  150. Class-incremental Learning for Time Series: Benchmark and Evaluation
  151. Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?
  152. Evaluation of ChatGPT's Smart Contract Auditing Capabilities Based on Chain of Thought
  153. A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change
  154. Training Green AI Models Using Elite Samples
  155. Cluster Metric Sensitivity to Irrelevant Features
  156. A Survey on Extractive Knowledge Graph Summarization: Applications, Approaches, Evaluation, and Future Directions
  157. ISCUTE: Instance Segmentation of Cables Using Text Embedding
  158. Network Inversion of Binarised Neural Nets
  159. Weakly Supervised Object Detection in Chest X-Rays with Differentiable ROI Proposal Networks and Soft ROI Pooling
  160. Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
  161. Universal generalization guarantees for Wasserstein distributionally robust models
  162. Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations
  163. Bayesian Active Learning for Censored Regression
  164. What Do Dialect Speakers Want? A Survey of Attitudes Towards Language Technology for German Dialects
  165. Imbalance in Regression Datasets
  166. DB-LLM: Accurate Dual-Binarization for Efficient LLMs
  167. Understanding the Therapeutic Relationship between Counselors and Clients in Online Text-based Counseling using LLMs
  168. Event-Based Motion Magnification
  169. Analysis of Multidomain Abstractive Summarization Using Salience Allocation
  170. Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels
  171. A novel molecule generative model of VAE combined with Transformer for unseen structure generation
  172. Mini-Hes: A Parallelizable Second-order Latent Factor Analysis Model
  173. LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation
  174. The effect of Leaky ReLUs on the training and generalization of overparameterized networks
  175. AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization
  176. Team QUST at SemEval-2024 Task 8: A Comprehensive Study of Monolingual and Multilingual Approaches for Detecting AI-generated Text
  177. SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised Learning
  178. Separating common from salient patterns with Contrastive Representation Learning
  179. Energy-Efficient Edge Learning via Joint Data Deepening-and-Prefetching
  180. A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task
  181. PhySU-Net: Long Temporal Context Transformer for rPPG with Self-Supervised Pre-training
  182. One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation
  183. Semantic Textual Similarity Assessment in Chest X-ray Reports Using a Domain-Specific Cosine-Based Metric
  184. Learning to Edit: Aligning LLMs with Knowledge Editing
  185. Automated Deterministic Auction Design with Objective Decomposition
  186. Real-World Planning with PDDL+ and Beyond
  187. SIBO: A Simple Booster for Parameter-Efficient Fine-Tuning
  188. Bridging or Breaking: Impact of Intergroup Interactions on Religious Polarization
  189. Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models
  190. Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint
  191. Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing
  192. ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding
  193. Generative Semi-supervised Graph Anomaly Detection
  194. The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth
  195. InMD-X: Large Language Models for Internal Medicine Doctors
  196. NOTE: Notable generation Of patient Text summaries through Efficient approach based on direct preference optimization
  197. M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation
  198. Language-guided Image Reflection Separation
  199. From Real World to Logic and Back: Learning Generalizable Relational Concepts For Long Horizon Robot Planning
  200. LoRA Training in the NTK Regime has No Spurious Local Minima
  201. Two Online Map Matching Algorithms Based on Analytic Hierarchy Process and Fuzzy Logic
  202. Stochastic Hessian Fittings with Lie Groups
  203. Communication-Efficient Distributed Learning with Local Immediate Error Compensation
  204. Modularized Networks for Few-shot Hateful Meme Detection
  205. WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detection
  206. CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking
  207. An Endoscopic Chisel: Intraoperative Imaging Carves 3D Anatomical Models
  208. An enhanced Teaching-Learning-Based Optimization (TLBO) with Grey Wolf Optimizer (GWO) for text feature selection and clustering
  209. UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction
  210. Self-Guided Robust Graph Structure Refinement
  211. DIO: Dataset of 3D Mesh Models of Indoor Objects for Robotics and Computer Vision Applications
  212. Rock Classification Based on Residual Networks
  213. Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios
  214. Microstructures and Accuracy of Graph Recall by Large Language Models
  215. Head-wise Shareable Attention for Large Language Models
  216. Where It Really Matters: Few-Shot Environmental Conservation Media Monitoring for Low-Resource Languages
  217. Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning
  218. HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?
  219. Interpretable Embedding for Ad-hoc Video Search
  220. FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema
  221. Generative Kaleidoscopic Networks
  222. SDGE: Stereo Guided Depth Estimation for 360^circ Camera Sets
  223. Statistical Test for Diffusion-Based Anomaly Localization via Selective Inference
  224. MM-SurvNet: Deep Learning-Based Survival Risk Stratification in Breast Cancer Through Multimodal Data Fusion
  225. CiMNet: Towards Joint Optimization for DNN Architecture and Configuration for Compute-In-Memory Hardware
  226. Towards Theoretical Understandings of Self-Consuming Generative Models
  227. Uncovering Latent Human Wellbeing in Language Model Embeddings
  228. FOD-Swin-Net: angular super resolution of fiber orientation distribution using a transformer-based deep model
  229. Dynamic Multi-Network Mining of Tensor Time Series
  230. Evaluating the Effectiveness of Index-Based Treatment Allocation
  231. ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs
  232. Large Language Models for Stemming: Promises, Pitfalls and Failures
  233. MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
  234. SPML: A DSL for Defending Language Models Against Prompt Attacks
  235. Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
  236. In-Context Learning Demonstration Selection via Influence Analysis
  237. Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptation
  238. Machine-Generated Text Localization