Papers
-
ICHOR: A Robust Representation Learning Approach for ASL CBF Maps with Self-Supervised Masked Autoencoders
-
CATNet: Collaborative Alignment and Transformation Network for Cooperative Perception
-
Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum
-
VietJobs: A Vietnamese Job Advertisement Dataset
-
A Behaviour-Aware Federated Forecasting Framework for Distributed Stand-Alone Wind Turbines
-
Beyond Word Error Rate: Auditing the Diversity Tax in Speech Recognition through Dataset Cartography
-
Visual-Informed Speech Enhancement Using Attention-Based Beamforming
-
Oral to Web: Digitizing 'Zero Resource'Languages of Bangladesh
-
SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm Reasoning
-
Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts
-
Layer by layer, module by module: Choose both for optimal OOD probing of ViT
-
Bayesian Supervised Causal Clustering
-
X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes
-
Knowledge Divergence and the Value of Debate for Scalable Oversight
-
STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks
-
WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces
-
Latent Policy Steering through One-Step Flow Policies
-
WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation
-
UniSTOK: Uniform Inductive Spatio-Temporal Kriging
-
Fusion4CA: Boosting 3D Object Detection via Comprehensive Image Exploitation
-
Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution
-
Latent-Mark: An Audio Watermark Robust to Neural Resynthesis
-
PersianPunc: A Large-Scale Dataset and BERT-Based Approach for Persian Punctuation Restoration
-
Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers
-
How important are the genes to explain the outcome - the asymmetric Shapley value as an honest importance metric for high-dimensional features
-
GALACTIC: Global and Local Agnostic Counterfactuals for Time-series Clustering
-
Machine Learning for analysis of Multiple Sclerosis cross-tissue bulk and single-cell transcriptomics data
-
FairFinGAN: Fairness-aware Synthetic Financial Data Generation
-
Dark3R: Learning Structure from Motion in the Dark
-
Bayes with No Shame: Admissibility Geometries of Predictive Inference
-
Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View
-
On the Statistical Optimality of Optimal Decision Trees
-
Preserving Continuous Symmetry in Discrete Spaces: Geometric-Aware Quantization for SO(3)-Equivariant GNNs
-
Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned
-
A Multilingual Human Annotated Corpus of Original and Easy-to-Read Texts to Support Access to Democratic Participatory Processes
-
Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation
-
InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context
-
Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR
-
DiSCTT: Consensus-Guided Self-Curriculum for Efficient Test-Time Adaptation in Reasoning
-
PACE: A Personalized Adaptive Curriculum Engine for 9-1-1 Call-taker Training
-
Progressive Residual Warmup for Language Model Pretraining
-
Learning Causal Structure of Time Series using Best Order Score Search
-
Embedded Inter-Subject Variability in Adversarial Learning for Inertial Sensor-Based Human Activity Recognition
-
Robust Node Affinities via Jaccard-Biased Random Walks and Rank Aggregation
-
OpenFrontier: General Navigation with Visual-Language Grounded Frontiers
-
PRISM: Personalized Refinement of Imitation Skills for Manipulation via Human Instructions
-
Prediction-Powered Conditional Inference
-
ORMOT: A Dataset and Framework for Omnidirectional Referring Multi-Object Tracking
-
Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations
-
Legal interpretation and AI: from expert systems to argumentation and LLMs
