Papers
-
ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K
-
MessyKitchens: Contact-rich object-level 3D scene reconstruction
-
Efficient Reasoning on the Edge
-
SegviGen: Repurposing 3D Generative Model for Part Segmentation
-
Demystifing Video Reasoning
-
WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation
-
LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings
-
Transformers Can Learn Rules They've Never Seen: Proof of Computation Beyond Interpolation
-
Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty
-
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
-
Shared Representation Learning for Reference-Guided Targeted Sound Detection
-
Dependence Fidelity and Downstream Inference Stability in Generative Models
-
OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materials
-
Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models
-
SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models
-
Attractor-Keyed Memory
-
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models
-
Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization
-
PaAgent: Portrait-Aware Image Restoration Agent via Subjective-Objective Reinforcement Learning
-
DesertFormer: Transformer-Based Semantic Segmentation for Off-Road Desert Terrain Classification in Autonomous Navigation Systems
-
Optimization-Embedded Active Multi-Fidelity Surrogate Learning for Multi-Condition Airfoil Shape Optimization
-
Transformers are Bayesian Networks
-
Evaluating Ill-Defined Tasks in Large Language Models
-
TrackDeform3D: Markerless and Autonomous 3D Keypoint Tracking and Dataset Collection for Deformable Objects
-
Edge-Efficient Two-Stream Multimodal Architecture for Non-Intrusive Bathroom Fall Detection
-
Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts
-
PRISM: Demystifying Retention and Interaction in Mid-Training
-
CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning
-
ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language Models
-
Ensemble Self-Training for Unsupervised Machine Translation
-
Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction
-
Accurate Shift Invariant Convolutional Neural Networks Using Gaussian-Hermite Moments
-
An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation
-
Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
-
When the Specification Emerges: Benchmarking Faithfulness Loss in Long-Horizon Coding Agents
-
LLM-Powered Flood Depth Estimation from Social Media Imagery: A Vision-Language Model Framework with Mechanistic Interpretability for Transportation Resilience
-
SENSE: Efficient EEG-to-Text via Privacy-Preserving Semantic Retrieval
-
Pixel-level Counterfactual Contrastive Learning for Medical Image Segmentation
-
Hidden Clones: Exposing and Fixing Family Bias in Vision-Language Model Ensembles
-
Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching
-
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
-
Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework
-
Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication
-
SMAL-pets: SMAL Based Avatars of Pets from Single Image
-
Contextual Preference Distribution Learning
-
REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge
-
Multilingual Reference Need Assessment System for Wikipedia
-
Personalized Fall Detection by Balancing Data with Selective Feedback Using Contrastive Learning
-
Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agents
-
Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints
