Large Language Models

Multiplicative learning from observation-prediction ratios

Automating quantum feature map design via large language models

Leakage and Interpretability in Concept-Based Models

GAIA: A Foundation Model for Operational Atmospheric Dynamics

Generalizable Heuristic Generation Through LLMs with Meta-Optimization

CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale

Learning The Minimum Action Distance

RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models

Graph Structure Learning with Privacy Guarantees for Open Graph Data

From Product Hilbert Spaces to the Generalized Koopman Operator and the Nonlinear Fundamental Lemma

From Context to Intent: Reasoning-Guided Function-Level Code Completion

DreamAudio: Customized Text-to-Audio Generation with Diffusion Models

MARS: toward more efficient multi-agent collaboration for LLM reasoning

VL-KnG: Persistent Spatiotemporal Knowledge Graphs from Egocentric Video for Embodied Scene Understanding

Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with Structured Output (SLSO) Framework

Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents

GUIrilla: A Scalable Framework for Automated Desktop UI Exploration

Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding

Quantifying Systemic Vulnerability in the Foundation Model Industry

Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs

MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding

HUMORCHAIN: Theory-Guided Multi-Stage Reasoning for Interpretable Multimodal Humor Generation

Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding

Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles

Arc Gradient Descent: A Geometrically Motivated Gradient Descent-based Optimiser with Phase-Aware, User-Controlled Step Dynamics (proof-of-concept)

Metaphor-based Jailbreak Attacks on Text-to-Image Models

Schr\"odinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation

AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents

VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing

Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic Search

Representational Homomorphism Predicts and Improves Compositional Generalization In Transformer Language Model

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance

FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning

Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation

Energy-Aware Reinforcement Learning for Robotic Manipulation of Articulated Components in Infrastructure Operation and Maintenance

KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG

When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift

Human Presence Detection via Wi-Fi Range-Filtered Doppler Spectrum on Commodity Laptops

NCCL EP: Towards a Unified Expert Parallel Communication API for NCCL

SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition

EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards

Elastic Weight Consolidation Done Right for Continual Learning

Mi:dm K 2.5 Pro

Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs

CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language