Papers
-
HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature
-
DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models
-
Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy
-
Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models
-
VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolution
-
Conformal Cross-Modal Active Learning
-
UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities
-
Dual Contrastive Network for Few-Shot Remote Sensing Image Scene Classification
-
PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learning
-
GSwap: Realistic Head Swapping with Dynamic Neural Gaussian Field
-
Robust Safety Monitoring of Language Models via Activation Watermarking
-
From Synthetic to Native: Benchmarking Multilingual Intent Classification in Logistics Customer Service
-
A Schrödinger Eigenfunction Method for Long-Horizon Stochastic Optimal Control
-
SAiW: Source-Attributable Invisible Watermarking for Proactive Deepfake Defense
-
APreQEL: Adaptive Mixed Precision Quantization For Edge LLMs
-
Gimbal360: Differentiable Auto-Leveling for Canonicalized $360^\circ$ Panoramic Image Completion
-
Reasoning over Semantic IDs Enhances Generative Recommendation
-
ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment
-
ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting
-
Gaze-Regularized VLMs for Ego-Centric Behavior Understanding
-
Wafer-Level Etch Spatial Profiling for Process Monitoring from Time-Series with Time-LLM
-
PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
-
The Geometric Price of Discrete Logic: Context-driven Manifold Dynamics of Number Representations
-
Sparser, Faster, Lighter Transformer Language Models
-
Residual Attention Physics-Informed Neural Networks for Robust Multiphysics Simulation of Steady-State Electrothermal Energy Systems
-
FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation
-
Gaze-Regularized Vision-Language-Action Models for Robotic Manipulation
-
Between Resolution Collapse and Variance Inflation: Weighted Conformal Anomaly Detection in Low-Data Regimes
-
A Latency Coding Framework for Deep Spiking Neural Networks with Ultra-Low Latency
-
Generative Inversion of Spectroscopic Data for Amorphous Structure Elucidation
-
PoseDriver: A Unified Approach to Multi-Category Skeleton Detection for Autonomous Driving
-
Decoding AI Authorship: Can LLMs Truly Mimic Human Style Across Literature and Politics?
-
General Machine Learning: Theory for Learning Under Variable Regimes
-
I Came, I Saw, I Explained: Benchmarking Multimodal LLMs on Figurative Meaning in Memes
-
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
-
GEM: Guided Expectation-Maximization for Behavior-Normalized Candidate Action Selection in Offline RL
-
MemCollab: Cross-Agent Memory Collaboration via Contrastive Trajectory Distillation
-
Online library learning in human visual puzzle solving
-
Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning
-
GO-Renderer: Generative Object Rendering with 3D-aware Controllable Video Diffusion Models
-
A Learning Method with Gap-Aware Generation for Heterogeneous DAG Scheduling
-
Is AI Catching Up to Human Expression? Exploring Emotion, Personality, Authorship, and Linguistic Style in English and Arabic with Six Large Language Models
-
AI Lifecycle-Aware Feasibility Framework for Split-RIC Orchestration in NTN O-RAN
-
Permutation-Symmetrized Diffusion for Unconditional Molecular Generation
-
MetaKube: An Experience-Aware LLM Framework for Kubernetes Failure Diagnosis
-
The Mass Agreement Score: A Point-centric Measure of Cluster Size Consistency
-
SynForceNet: A Force-Driven Global-Local Latent Representation Framework for Lithium-Ion Battery Fault Diagnosis
-
SafeSeek: Universal Attribution of Safety Circuits in Language Models
-
Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
-
A Multimodal Framework for Human-Multi-Agent Interaction
KiloClaw - Managed 🦀 