Loading timeline…
Loading timeline…
Events grouped by month, newest first. Every entry links to the entity and to the source that stated the change.
400 events
Year
Category · events in the last 365 days
PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving: arxiv announce type changed from cross to replace
CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search: arxiv announce type changed from new to cross
MultiHuSE: A Multimodal Dataset for Humour Styles and Emotions: arxiv announce type changed from new to cross
OmniHallu: Unified Hallucination Detection for Cross-Modal Comprehension and Generation in Multimodal Large Language Models: arxiv announce type changed from new to cross
RiVaT-Fuse: Reliability-Calibrated Variational Tensor Fusion for Multimodal Prediction under Modality Uncertainty: arxiv announce type changed from new to cross
M3-Former: Multimodal Transformer with Mixture-of-Experts for Long-Term Vessel Trajectory Prediction: arxiv announce type changed from new to cross
3D Point Splatting for mmWave Radar Novel View Synthesis: arxiv announce type changed from cross to new
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling: arxiv announce type changed from cross to new
Multimodal Taxonomic Conditioning for Generative Plankton Imagery: arxiv announce type changed from cross to new
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation: arxiv announce type changed from cross to new
Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language Models: arxiv announce type changed from cross to new
Improving Faint Object Detection for Space Situational Awareness with Variational Autoencoders: arxiv announce type changed from cross to new
TailProp: content-adaptive light- and heavy-tailed propagation for vision: arxiv announce type changed from cross to new
Meta-Learning for Classifier Selection in Image Datasets: A Feature-Driven Framework for Accuracy Prediction: arxiv announce type changed from cross to new
New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models: arxiv announce type changed from cross to new
Symmetry-aware super-resolution of crystal orientation maps via invariant latent-space learning: arxiv announce type changed from cross to new
Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptions: arxiv announce type changed from cross to new
BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation: arxiv announce type changed from cross to new
How Much Velocity Does Off-Ball Space Value Need? A Broadcast-Viewport Benchmark: arxiv announce type changed from cross to new
Meta-Learning for Data-Efficient Plant Growth Estimation via Vision Transformers and Fuzzy Clustering: arxiv announce type changed from cross to new
Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements: arxiv announce type changed from replace to cross
Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data: arxiv announce type changed from new to cross
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement: arxiv announce type changed from new to cross
Why Does Post-Training Quantization Work?: arxiv announce type changed from new to cross
MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions: arxiv announce type changed from new to cross
REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving: arxiv announce type changed from new to cross
LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry: arxiv announce type changed from new to cross
Beyond Solver Verdicts: Generative Reward Models for Autoformalization: arxiv announce type changed from new to cross
The information geometry of large language models is shared, learned, and controllable: arxiv announce type changed from new to cross
Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble: arxiv announce type changed from new to cross
The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes: arxiv announce type changed from new to cross
Artificial Intelligence Algorithms for the Detection of Pathologies Related to Lung Cancer through Image Analysis using Convolutional Neural Networks and Data Augmentation: a systematic mapping of the literature: arxiv announce type changed from new to cross
Domain-Specific Hallucination Detection in Large Language Models: arxiv announce type changed from cross to new
LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation: arxiv announce type changed from cross to new
Negative Self-Distillation: Learning to Reason by Avoiding Flaws: arxiv announce type changed from cross to new
Structural priors for data-efficient language learning: arxiv announce type changed from cross to new
E-CONAN (Entailment, CONtradition And Neutral) Benchmarks: Arabic Textual Entailment and Natural Inference Datasets: arxiv announce type changed from cross to new
A Fragility Spectrum for Recursive Language-Model Training: arxiv announce type changed from cross to new
When Noise Fabricates Bias: The Fragility of LLM-as-a-Judge Bias Measurement under Noisy Text: arxiv announce type changed from cross to new
Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy Loss: arxiv announce type changed from cross to new
Robust Multimodal Sentiment Analysis with Incomplete Modalities via Semantic-aware Completeness based Reconstruction: arxiv announce type changed from cross to new
Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation: arxiv announce type changed from cross to new
Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models: arxiv announce type changed from cross to new
Multilingual in Name Only? Cultural and Linguistic Weaknesses of LLMs in Urdu: arxiv announce type changed from cross to new
New paper: Data-Driven Risk Fields for Safer End-to-End Autonomous Driving
New paper: TBR: Transport-Based Rendering with Deposition Strokes for Inverse Graphics
New paper: Diagnosing and Dynamically Filtering Occupancy World Models for Active Mapping
New paper: Measuring Browser Webcam Gaze Honestly: A Capture-Clock Methodology and Open Reference Implementation
New paper: SGA: Plug&Play Geometric Verification for Educational Video Synthesis
New paper: Domain Elastic Transform: Bayesian Function Registration for High-Dimensional Scientific Data
New paper: DefVINS: Visual-Inertial Odometry for Deformable Scenes
New paper: DCReg: Decoupled Characterization for Efficient Degenerate LiDAR Registration
New paper: Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation
New paper: FastMap: Real-Time Semantic Map Completion via Bitwise Masked Modeling
New paper: Towards AI-Driven Policing: Interdisciplinary Knowledge Discovery from Police Body-Worn Camera Footage
New paper: PathoHR: Breast Cancer Survival Prediction on High-Resolution Pathological Images
New paper: SegKAN: High-Resolution Medical Image Segmentation with Long-Distance Dependencies
New paper: 3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity Estimation
New paper: From Few-Shot Segmentation to Clinician-in-the-Loop Medical Image Analysis
New paper: Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model
New paper: Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision
New paper: CGSM: Concept-Guided Segmentation Model for Precise Pulmonary Lesion Delineation
New paper: RAIDAL: Redundancy-Aware Information Density Active Learning for CTC-Based Continuous Sign Language Recognition
New paper: FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian Splatting
New paper: FreeTransformSR: Efficient Lightweight Image Super-Resolution via Free Low-Rank Learnable Transform
New paper: Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System
New paper: Design and Implementation of a Kalman Filter-Infused Algorithm for Tilt Estimation
New paper: Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstruction
New paper: A Calibration Audit of Confidence in Feed-Forward 3D Reconstruction Models
New paper: Differentiable Jitter Correction using Deep Learning-based Image Quality Metric for Phase-Contrast Micro-CT
New paper: MRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven Characterization
New paper: Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding
New paper: StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs
New paper: TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
New paper: SparSTAR: Sparse Attention for SpaceTime AutoRegressive Video Synthesis
New paper: SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models
New paper: SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
New paper: HeteroPROMPT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception Framework
New paper: ScaleResfusion: Residual Rectified Flow based on Residual Vector Field
New paper: Does YOLO26 Truly Offer Advantages Over Its Predecessors for Edge Deployment? A Benchmark Study in Aquaculture
New paper: ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation
New paper: Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learning
New paper: TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards
New paper: Reconstruction of a 3D wireframe from a single line drawing via generative depth estimation
New paper: Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks
New paper: Towards Automated Solar Panel Integrity: Hybrid Deep Feature Extraction for Advanced Surface Defect Identification
New paper: Automated multi-class wound assessment using dedicated instance segmentation models for boundary detection and classification
New paper: Leveraging Avatar Fingerprinting: A Multi-Generator Photorealistic Talking-Head Public Database and Benchmark
New paper: CLIP-RD: Relational Distillation for Efficient CLIP Knowledge Distillation
New paper: InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D Reconstruction
New paper: V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval
New paper: Gaussian Belief Propagation Network for Depth Completion
New paper: DirectSwap: Paired, Mask-Free Video Head Swapping with Full-Reference Evaluation
New paper: MedGEN-Bench: A Contextually Entangled Benchmark for Open-ended Multimodal Medical Generation
New paper: Confidence-Calibrating Regularization for Robust Brain MRI Segmentation Under Domain Shift
New paper: Adaptive Dual-Constrained Line Aggregation for Cross-Paradigm Line Segment Detection
New paper: Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation
New paper: SSS: Semi-Supervised SAM-2 with Efficient Prompting for Medical Imaging Segmentation
New paper: SegCol Challenge: Semantic Segmentation for Tools and Fold Edges in Colonoscopy data
New paper: AI-Powered Flare Combustion Efficiency Estimation
New paper: Exponential Pixelating Integral transform with dual fractal features for enhanced chest X-ray abnormality detection
New paper: IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies
New paper: Seamless Whole Slide Label-Free Virtual Staining
New paper: SenseNova-U1.5: Towards Native Unified Visual Intelligence
New paper: Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding
New paper: Guided Super-Resolution of Digital Elevation Models with Diffusion-Based Image Generators
New paper: Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need
New paper: MC-DeTra: Motion-Consistent Joint Object Detection and Socially-Aware Trajectory Forecasting in Bird's-Eye-View Images
New paper: Language-Augmented Semantic Priors for B-Spline Surface Fitting
New paper: Spectral Adapters for Segment Anything Model-based Segmentation of Colorectal Liver Metastases in Computed Tomography
New paper: Single-Stream Multi-Feature Fusion with Temporal Robustness for Gait Emotion Recognition
New paper: Self-Supervised Cardiac Phase Detection via Single-Parameter Latent Orbits
New paper: LangStreet: Persistent Language Fields for Anchor-Decoded Street Gaussians
New paper: MMGait: Benchmarking and Unifying Gait Recognition across Heterogeneous Modalities
New paper: OmniKVQuant: KV Cache Quantization for Omni-LLMs
New paper: Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
New paper: A Comparative Evaluation of Pre-trained Convolutional Neural Networks for Melanoma Detection
New paper: World in World: Explore the World with World Models
New paper: Learning Interaction between Image and Layout Priors for Joint Image-Layout Generation in Design Templates
New paper: LoopVAE: Recurrent Depth Across Scales for Visual Tokenization
New paper: Prototype Matters: Modality-unified Prototype Self-distillation for Unsupervised Visible-infrared Person Re-identification
New paper: Harnessing Intrinsic Subject-Aware Attention for Controllable Multi-Subject Video Generation
New paper: UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound
New paper: Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs
New paper: FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation
New paper: Pre- and Post-Treatment Brain Metastases Segmentation Using nnU-Net with Post-Processing for BraTS 2026
New paper: BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration
New paper: BruNet: A Cross-Domain Transfer Framework for Bruise Segmentation
New paper: Multi-Modal Controlled Coherent Motion Generation
New paper: DINO-Med: A Unified Patch-Based Adaptation Framework for Multi-Modal Medical Image Analysis Applied to Liver Fibrosis Staging
New paper: Brain-PACE: A Deep Siamese MRI Framework for Modelling Longitudinal Brain Acceleration
New paper: Vision Transformer-Based Multi-Level Feature Fusion for Multi-Label Sewer Defect Classification
New paper: R4Tun: LLM-guided adaptive segmental tunnel lining segmentation in point clouds
New paper: Predictive Multi-Landmark OCT Tracking for Increased Motion Robustness
New paper: Mi-Ripple: Restoring Images Degraded by Iterative AI Editing
New paper: GRIPNet: Gaussian Radial Intensity Prior Guided Architecture for Pulmonary Nodule Detection in CT
New paper: SAMV-DUSt3R: Instance-Centric 3D Scene Decoupling from Sparse Multi-Views
New paper: Order-Aware 2.5D Multiple Instance Learning for Preoperative MRI-Based Perineural Invasion Risk Assessment in Intrahepatic Cholangiocarcinoma
New paper: Uncertainty DMD: Restoring Diversity in Few-Step Autoregressive Video Distillation
New paper: From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models
New paper: Fast and Accurate Monomodal 3D High Resolution Deep Registration of Drosophila Larval Brain Volumes
New paper: SCINTILLA-SNN: A Spiking Multi-Scale Selective Aggregation Network for Perineural Invasion Prediction
New paper: HALDETECT at ImageEval 2026 Shared Tasks: Answer-First Contrastive Grounding with QLoRA
New paper: When is Test-Time Adaptation Identifiable From Unlabeled Evidence?
New paper: Tri-DehazeGS: Scene--Medium Decoupled Gaussian Splatting with Transmittance-Aware Optimization
New paper: CEM-TUDASR: Computationally efficient multi-modality transformer based unsupervised domain adaptive super-resolution approach
New paper: A Multi-View and Confusion-Guided Ensemble Framework for Robust Synthetic Image Attribution
New paper: Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval
New paper: UniH$^3$: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration
New paper: LAION-Mobile: Evaluating Deepfake Detectors On One Million Smartphone Photos
New paper: ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation
New paper: Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions
New paper: Toward Interpretable Multimodal Fusion: Heat Conduction Modeling for Hyperspectral and LiDAR Joint Classification
New paper: CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation
New paper: HiPerViT: A Hierarchical Perceiver-Vision Transformer Architecture for Multi-Scale Texture Recognition
New paper: Evaluation of Vision-Language Models Across Diverse Coastal Environments
New paper: Overpainting: Localized Context-aware Diffusion Image Editing
New paper: TrajFusionNet+: Transformer-Based Prediction of Pedestrian Crossing Intention via Fusion of Trajectory Representations and Scene Graphs
New paper: Two-Parameter Flow Map Learning for Continuous-Time Diffeomorphic Image Registration
New paper: Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Models
New paper: GRADE: Single-Frame Generative Radar Depth Estimation Under Visual Degradation
New paper: MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery
New paper: AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow
New paper: Rethinking Handwritten Character Recognition
New paper: Omni Interaction Agent Technical Report
New paper: Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling
New paper: SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities
New paper: Fine PT-PT Web: A High-Quality 41 Billion Tokens Data Collection of the European Portuguese Web
New paper: Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMs
New paper: When Does a Laugh Begin? Structured Annotator Disagreement in Temporal Laughter Localization
New paper: PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation
New paper: VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models
New paper: Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach
New paper: Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classification
New paper: Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
New paper: LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
New paper: AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP
New paper: 'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
New paper: tinyDSM: A Framework for Skill Modeling and Development for Resource-Constrained Millirobots
New paper: Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning
New paper: Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability
New paper: Chameleon: An Adaptive AI-Driven Honeypot Architecture Using Threat-Calibrated Particle Swarm Optimization and Semantic Deception Rapidly-Exploring Random Trees
New paper: Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models
New paper: DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation
New paper: PRIME-SVR: Physics-infoRmed Implicit Multi-Echo Slice-to-Volume Reconstruction for Fetal T2 mapping
New paper: Builder, Defender, Breaker: Measurable Independence and Bounded Autonomy When Generative Models Build, Defend and Test Software
New paper: Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning
New paper: FP8 is All You Need (Part 2): Full-FP64 3-D FFT on FP8-Generation Tensor CoresThe Integer-Epilogue Wall and the Minimal Hardware That Would Remove It
New paper: PSCT-Net: Geometry-Aware Pediatric Skull CT Reconstruction via Differentiable Back-Projection and Attention-Guided Refinement
New paper: Expert-Level Crisis Detection in Mental Health Conversations
Showing up to 400 events. Narrow by year or category, or use the changes feed for cursor-paged history. Times are UTC.