mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 5 Dec 2023

270 papers

  1. Exploring Social Bias in Downstream Applications of Text-to-Image Foundation ModelsDiffusion models → Image generation, text-to-image and editing
  2. DiffusionAtlas: High-Fidelity Consistent Diffusion Video EditingDiffusion models → Video generation
  3. DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  4. Visual Hindsight Self-Imitation Learning for Interactive NavigationOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  5. Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  6. FlexModel: A Framework for Interpretability of Distributed Large Language ModelsMechanistic interpretability → Knowledge and representations inside LLMs
  7. Evaluating Agents using Social Choice TheoryLLM agents and tool use → Social simulation and multi-agent debate
  8. LooseControl: Lifting ControlNet for Generalized Depth ConditioningDiffusion models → Image generation, text-to-image and editing
  9. Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  10. Generating Interpretable Networks using HypernetworksMechanistic interpretability → Circuits and mechanistic analysis
  11. DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic ControlDiffusion models → Medical imaging and segmentation
  12. Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?End-to-end autonomous driving → End-to-end system architecture
  13. Stable Diffusion Exposed: Gender Bias from Prompt to ImageDiffusion models → Image generation, text-to-image and editing
  14. Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph ConstructionLLM agents and tool use → Web, search, and research agents
  15. DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text GuidanceDiffusion models → Video generation
  16. ReconFusion: 3D Reconstruction with Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  17. GPT4Point: A Unified Framework for Point-Language Understanding and GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  18. SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real WorldOffline RL and imitation learning from data → Imitation learning methods
  19. Alchemist: Parametric Control of Material Properties with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  20. AmbiGen: Generating Ambigrams from Pre-trained Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  21. Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object DetectionDiffusion models → Image generation, text-to-image and editing +1
  22. LLaVA-Grounding: Grounded Visual Chat with Large Multimodal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  23. BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal ModelsLLM reasoning → Multimodal reasoning +1
  24. MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in SuperpositionMechanistic interpretability → Sparse autoencoder training and evaluation
  25. BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion ModelsDiffusion models → Video generation
  26. FG-MDM: Towards Zero-Shot Human Motion Generation via ChatGPT-Refined DescriptionsDiffusion models → Video generation
  27. Neural Sign Actors: A diffusion model for 3D sign language production from textDiffusion models → Sign language production
  28. Analyzing and Improving the Training Dynamics of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  29. Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based SamplerDiffusion models → Audio, speech and music
  30. TPA3D: Triplane Attention for Fast Text-to-3D GenerationDiffusion models → 3D, point cloud and scene generation
  31. Rethinking and Simplifying Bootstrapped Graph LatentsSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  32. Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion ModelsDiffusion models → Flow matching, time series and science
  33. ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise PreferenceLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  34. GeNIe: Generative Hard Negative Images Through DiffusionDiffusion models → Image generation, text-to-image and editing
  35. Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  36. DRAFT: Dense Retrieval Augmented Few-shot Topic classifier FrameworkRetrieval-augmented generation → Generation and context integration
  37. Creative Agents: Empowering Agents with Imagination for Creative TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  38. Design and Evaluation of an Uncertainty-Aware Shared-Autonomy System with Hierarchical Conservative Skill InferenceOffline RL and imitation learning from data → Robot manipulation imitation learning
  39. EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language ModelMultimodal LLMs / vision-language models → Video understanding with MLLMs
  40. Fast non-autoregressive inverse folding with discrete diffusionDiffusion models → Flow matching, time series and science
  41. Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor GenerationLLM reasoning → Reasoning benchmarks and evaluation
  42. Lenna: Language Enhanced Reasoning Detection AssistantLLM reasoning → Multimodal reasoning +1
  43. Orthogonal Adaptation for Modular Customization of Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  44. MATE-Pred: Multimodal Attention-based TCR-Epitope interaction Predictor
  45. Flood Event Extraction from News Media to Support Satellite-Based Flood Insurance
  46. Liquid State Genetic Programming
  47. Multi-Criteria Client Selection and Scheduling with Fairness Guarantee for Federated Learning Service
  48. Artificial Neural Network for Estimation of Physical Parameters of Sea Water using LiDAR Waveforms
  49. Teenagers and Artificial Intelligence: Bootcamp Experience and Lessons Learned
  50. Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety
  51. Optimizing Fault-Tolerant Quality-Guaranteed Sensor Deployments for UAV Localization in Critical Areas via Computational Geometry
  52. All Rivers Run to the Sea: Private Learning with Asymmetric Flows
  53. Model Copyright Protection in Buyer-seller Environment
  54. Toward Energy-Efficient Massive MIMO: Graph Neural Network Precoding for Mitigating Non-Linear PA Distortion
  55. Reconciling AI Performance and Data Reconstruction Resilience for Medical Imaging
  56. GPT vs Human for Scientific Reviews: A Dual Source Review on Applications of ChatGPT in Science
  57. Unknown Sample Discovery for Source Free Open Set Domain Adaptation
  58. Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment
  59. Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning
  60. Gaussian3Diff: 3D Gaussian Diffusion for 3D Full Head Synthesis and Editing
  61. Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study
  62. Learning High-Dimensional Differential Graphs From Multi-Attribute Data
  63. How should the advent of large language models affect the practice of science?
  64. FERGI: Automatic Scoring of User Preferences for Text-to-Image Generation from Spontaneous Facial Expression Reaction
  65. Data-Driven Traffic Reconstruction and Kernel Methods for Identifying Stop-and-Go Congestion
  66. CaloQVAE : Simulating high-energy particle-calorimeter interactions using hybrid quantum-classical generative models
  67. Active Learning for Abrupt Shifts Change-point Detection via Derivative-Aware Gaussian Processes
  68. A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education
  69. Combining Counting Processes and Classification Improves a Stopping Rule for Technology Assisted Review
  70. Adaptive spectral graph wavelets for collaborative filtering
  71. Deep Learning for Fast Inference of Mechanistic Models' Parameters
  72. HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces
  73. Algorithmic Fairness with Feedback
  74. ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet
  75. Multitask Learning Can Improve Worst-Group Outcomes
  76. Neural parameter calibration and uncertainty quantification for epidemic forecasting
  77. Maximum likelihood thresholds of Gaussian graphical models and graphical lasso
  78. A Hardware Evaluation Framework for Large Language Model Inference
  79. Predicting Bone Degradation Using Vision Transformer and Synthetic Cellular Microstructures Dataset
  80. Assertion Enhanced Few-Shot Learning: Instructive Technique for Large Language Models to Generate Educational Explanations
  81. The Landscape of Modern Machine Learning: A Review of Machine, Distributed and Federated Learning
  82. AI-SAM: Automatic and Interactive Segment Anything Model
  83. The Automated Bias Triangle Feature Extraction Framework
  84. Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI
  85. What Causes Polysemanticity? An Alternative Origin Story of Mixed Selectivity from Incidental Causes
  86. Understanding Environmental Posts: Sentiment and Emotion Analysis of Social Media Data
  87. RESIN-EDITOR: A Schema-guided Hierarchical Event Graph Visualizer and Editor
  88. LLMs for Multi-Modal Knowledge Extraction and Analysis in Intelligence/Safety-Critical Applications
  89. ScAR: Scaling Adversarial Robustness for LiDAR Object Detection
  90. Clinical Notes Reveal Physician Fatigue
  91. Advantage of Quantum Machine Learning from General Computational Advantages
  92. Adaptive Multi-step Refinement Network for Robust Point Cloud Registration
  93. HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding
  94. MagicStick: Controllable Video Editing via Control Handle Transformations
  95. Diversified in-domain synthesis with efficient fine-tuning for few-shot classification
  96. Customization Assistant for Text-to-image Generation
  97. REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training
  98. Navigating the Synthetic Realm: Harnessing Diffusion-based Models for Laparoscopic Text-to-Image Generation
  99. Inherent limitations of LLMs regarding spatial information
  100. Transformer-Based Deep Learning Model for Bored Pile Load-Deformation Prediction in Bangkok Subsoil
All 270
  1. Sample-based Dynamic Hierarchical Transformer with Layer and Head Flexibility via Contextual Bandit
  2. SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction
  3. LiDAR-based Person Re-identification
  4. ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models
  5. Generating Visually Realistic Adversarial Patch
  6. HHAvatar: Gaussian Head Avatar with Dynamic Hairs
  7. Double Integral Enhanced Zeroing Neural Network Optimized with ALSOA fostered Lung Cancer Classification using CT Images
  8. Uni3DL: Unified Model for 3D and Language Understanding
  9. Training on Synthetic Data Beats Real Data in Multimodal Relation Extraction
  10. Enhanced Breast Cancer Tumor Classification using MobileNetV2: A Detailed Exploration on Image Intensity, Error Mitigation, and Streamlit-driven Real-time Deployment
  11. AI-driven emergence of frequency information non-uniform distribution via THz metasurface spectrum prediction
  12. Protein Language Model-Powered 3D Ligand Binding Site Prediction from Protein Sequence
  13. PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation
  14. Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey
  15. Breast Ultrasound Report Generation using LangChain
  16. Dexterous Functional Grasping
  17. Describing Differences in Image Sets with Natural Language
  18. GauHuman: Articulated Gaussian Splatting from Monocular Human Videos
  19. Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models
  20. MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures
  21. Detecting algorithmic bias in medical-AI models using trees
  22. Classification for everyone : Building geography agnostic models for fairer recognition
  23. Choroidalyzer: An open-source, end-to-end pipeline for choroidal analysis in optical coherence tomography
  24. Calibrating dimension reduction hyperparameters in the presence of noise
  25. Fast CT anatomic localization algorithm
  26. Drag-A-Video: Non-rigid Video Editing with Point-based Interaction
  27. WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation
  28. WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words
  29. LivePhoto: Real Image Animation with Text-guided Motion Control
  30. MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning
  31. Fine-grained Controllable Video Generation via Object Appearance and Context
  32. Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration
  33. MIND: Multi-Task Incremental Network Distillation
  34. Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training
  35. Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions
  36. Realistic Scatterer Based Adversarial Attacks on SAR Image Classifiers
  37. Rare Galaxy Classes Identified In Foundation Model Representations
  38. Deep Learning Segmentation of Spiral Arms and Bars
  39. HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting
  40. Concept Drift Adaptation in Text Stream Mining Settings: A Systematic Review
  41. Towards More Practical Group Activity Detection: A New Benchmark and Model
  42. DIPR: Efficient Point Cloud Registration via Dynamic Iteration
  43. Toward autocorrection of chemical process flowsheets using large language models
  44. Experimental Insights Towards Explainable and Interpretable Pedestrian Crossing Prediction
  45. Attention-enhanced neural differential equations for physics-informed deep learning of ion transport
  46. Can a Tabula Recta provide security in the XXI century?
  47. Semi-Supervised Health Index Monitoring with Feature Generation and Fusion
  48. Lessons from Usable ML Deployments and Application to Wind Turbine Monitoring
  49. Towards Causal Representations of Climate Model Data
  50. Exploring Error Bits for Memory Failure Prediction: An In-Depth Correlative Study
  51. Expert-guided Bayesian Optimisation for Human-in-the-loop Experimental Design of Known Systems
  52. A Kernel-Based Neural Network Test for High-dimensional Sequencing Data Analysis
  53. Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space
  54. Are Vision Transformers More Data Hungry Than Newborn Visual Systems?
  55. Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications
  56. Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis
  57. RotaTR: Detection Transformer for Dense and Rotated Object
  58. Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix
  59. Deterministic Guidance Diffusion Model for Probabilistic Weather Forecasting
  60. Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability
  61. Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic
  62. Weakly Supervised Detection of Hallucinations in LLM Activations
  63. Materials Expert-Artificial Intelligence for Materials Discovery
  64. Machine Learning Driven Sensitivity Analysis of E3SM Land Model Parameters for Wetland Methane Emissions
  65. Large Language Models on Graphs: A Comprehensive Survey
  66. PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features
  67. Scaling Laws for Adversarial Attacks on Language Model Activations
  68. Learning "Look-Ahead" Nonlocal Traffic Dynamics in a Ring Road
  69. Learning Cortical Anomaly through Masked Encoding for Unsupervised Heterogeneity Mapping
  70. C3: High-performance and low-complexity neural compression from a single image or video
  71. C-NERF: Representing Scene Changes as Directional Consistency Difference-based NeRF
  72. Compositional Generalization for Data-to-Text Generation
  73. LExCI: A Framework for Reinforcement Learning with Embedded Systems
  74. Towards Measuring Representational Similarity of Large Language Models
  75. R3D-SWIN:Use Shifted Window Attention for Single-View 3D Reconstruction
  76. Towards the Inferrence of Structural Similarity of Combinatorial Landscapes
  77. Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
  78. Large Knowledge Model: Perspectives and Challenges
  79. Unified learning-based lossy and lossless JPEG recompression
  80. MyPortrait: Morphable Prior-Guided Personalized Portrait Generation
  81. Revisit Human-Scene Interaction via Space Occupancy
  82. Enhancing Vehicle Entrance and Parking Management: Deep Learning Solutions for Efficiency and Security
  83. UPOCR: Towards Unified Pixel-Level OCR Interface
  84. DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors
  85. H-GAP: Humanoid Control with a Generalist Planner
  86. Contact Energy Based Hindsight Experience Prioritization
  87. Amortized Bayesian Decision Making for simulation-based models
  88. Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?
  89. Learning a Sparse Representation of Barron Functions with the Inverse Scale Space Flow
  90. Lights out: training RL agents robust to temporary blindness
  91. FaceStudio: Put Your Face Everywhere in Seconds
  92. A Self-Commissioning Edge Computing Method for Data-Driven Anomaly Detection in Power Electronic Systems
  93. Supervised learning of spatial features with STDP and homeostasis using Spiking Neural Networks on SpiNNaker
  94. Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciar'an
  95. What Machine Learning Can Do for Focusing Aerogel Detectors
  96. A Q-learning approach to the continuous control problem of robot inverted pendulum balancing
  97. SAMSGL: Series-Aligned Multi-Scale Graph Learning for Spatio-Temporal Forecasting
  98. Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs
  99. Diffusion Noise Feature: Accurate and Fast Generated Image Detection
  100. On the Initialization of Graph Neural Networks
  101. DreaMo: Articulated 3D Reconstruction From A Single Casual Video
  102. Facilitating the Production of Well-tailored Video Summaries for Sharing on Social Media
  103. Prompt Optimization via Adversarial In-Context Learning
  104. A Unified Simulation Framework for Visual and Behavioral Fidelity in Crowd Analysis
  105. Privacy-Aware Data Acquisition under Data Similarity in Regression Markets
  106. Panoptica -- instance-wise evaluation of 3D semantic and instance segmentation maps
  107. Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation
  108. Impact of Tokenization on LLaMa Russian Adaptation
  109. LSTSVR-PI: Least square twin support vector regression with privileged information
  110. FRAPPE: A Group Fairness Framework for Post-Processing Everything
  111. Text Intimacy Analysis using Ensembles of Multilingual Transformers
  112. Empathy and Distress Detection using Ensembles of Transformer Models
  113. An Integrated System for Spatio-Temporal Summarization of 360-degrees Videos
  114. UTBoost: Gradient Boosted Decision Trees for Uplift Modeling
  115. Prompt2NeRF-PIL: Fast NeRF Generation via Pretrained Implicit Latent
  116. Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts
  117. Structured World Representations in Maze-Solving Transformers
  118. DanZero+: Dominating the GuanDan Game through Reinforcement Learning
  119. DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
  120. On Optimal Consistency-Robustness Trade-Off for Learning-Augmented Multi-Option Ski Rental
  121. Graph Information Bottleneck for Remote Sensing Segmentation
  122. Characterization of Locality in Spin States and Forced Moves for Optimizations
  123. Explainable Severity ranking via pairwise n-hidden comparison: a case study of glaucoma
  124. Asymmetric leader-laggard cluster synchronization for collective decision-making with laser network
  125. Towards Open-set Gesture Recognition via Feature Activation Enhancement and Orthogonal Prototype Learning
  126. PolyFit: A Peg-in-hole Assembly Framework for Unseen Polygon Shapes via Sim-to-real Adaptation
  127. MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection
  128. Towards Automatic Power Battery Detection: New Challenge, Benchmark Dataset and Baseline
  129. MASP: Scalable GNN-based Planning for Multi-Agent Navigation
  130. RetriBooru: Leakage-Free Retrieval of Conditions from Reference Images for Subject-Driven Generation
  131. Towards More Unified In-context Visual Understanding
  132. Simplifying Neural Network Training Under Class Imbalance
  133. mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs
  134. AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation
  135. SAVE: Protagonist Diversification with Structure Agnostic Video Editing
  136. Inspecting Model Fairness in Ultrasound Segmentation Tasks
  137. MKA: A Scalable Medical Knowledge Assisted Mechanism for Generative Models on Medical Conversation Tasks
  138. ReconU-Net: a direct PET image reconstruction using U-Net architecture with back projection-induced skip connection
  139. Flexible Communication for Optimal Distributed Learning over Unpredictable Networks
  140. Pseudo Replay-based Class Continual Learning for Online New Category Anomaly Detection in Advanced Manufacturing
  141. Constrained Twin Variational Auto-Encoder for Intrusion Detection in IoT Systems
  142. Learning to Holistically Detect Bridges from Large-Size VHR Remote Sensing Imagery
  143. Differentiable Point-based Inverse Rendering
  144. RL-Based Cargo-UAV Trajectory Planning and Cell Association for Minimum Handoffs, Disconnectivity, and Energy Consumption
  145. NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams
  146. Congestion-aware Distributed Task Offloading in Wireless Multi-hop Networks Using Graph Neural Networks
  147. Generator Born from Classifier
  148. Learning Energy-based Model via Dual-MCMC Teaching
  149. SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary Constraints
  150. Dimensionality Reduction and Dynamical Mode Recognition of Circular Arrays of Flame Oscillators Using Deep Neural Network
  151. GIT-Net: Generalized Integral Transform for Operator Learning
  152. E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendation
  153. MedDM:LLM-executable clinical guidance tree for clinical decision-making
  154. Adaptive Instrument Design for Indirect Experiments
  155. GDN: A Stacking Network Used for Skin Cancer Diagnosis
  156. MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following
  157. FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functions
  158. Visually Grounded Language Learning: a review of language games, datasets, tasks, and models
  159. PEFA: Parameter-Free Adapters for Large-scale Embedding-based Retrieval Models
  160. FreestyleRet: Retrieving Images from Style-Diversified Queries
  161. Repurposing SAM for User-Defined Semantics Aware Segmentation
  162. Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data
  163. Near-Optimal Mean Estimation with Unknown, Heteroskedastic Variances
  164. Towards Fast and Stable Federated Learning: Confronting Heterogeneity via Knowledge Anchor
  165. MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR
  166. Robust Clustering using Hyperdimensional Computing
  167. Efficient Online Data Mixing For Language Model Pre-Training
  168. BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
  169. Enhancing Content Moderation with Culturally-Aware Models
  170. DP-SGD-Global-Adapt-V2-S: Triad Improvements of Privacy, Accuracy and Fairness via Step Decay Noise Multiplier and Step Decay Upper Clipping Threshold