3607 papers
This paper introduces NAAMSE, an evolutionary framework that automates and enhances AI agent security evaluation by using a single autonomous agent to iteratively mutate prompts and explore corpora, thereby uncovering adaptive vulnerabilities missed by static benchmarks while ensuring the models maintain benign-use correctness.
PhysDrape is a hybrid neural-physical solver that combines a Physics-Informed Graph Neural Network with a differentiable two-stage force and collision projection system to achieve physically realistic garment draping with negligible interpenetration and superior fidelity compared to existing deep learning methods.
LLM4PQC is a feedback-driven, agentic framework that leverages large language models to automate the refactoring of complex post-quantum cryptography reference codes into synthesizable HLS specifications and RTL, significantly reducing manual effort and accelerating design-space exploration through a hierarchical verification process.
To address the challenges of parameter-efficient domain adaptation in V2X collaborative perception, the paper proposes FlowAdapt, a framework leveraging optimal transport theory and a progressive knowledge transfer mechanism to filter redundant data and preserve fine-grained semantics, achieving state-of-the-art performance with only 1% trainable parameters.
This paper proposes SToRM, a novel framework that employs a lightweight importance predictor, supervised training with pseudo-labels, and an anchor-context merging module to significantly reduce visual token redundancy in multi-modal LLMs for autonomous driving, achieving up to 30x computational savings while maintaining end-to-end performance comparable to using all tokens.
This paper introduces Agent-guided Policy Search (AGPS), a framework that replaces human supervisors with a multimodal agent acting as a semantic world model to provide precise corrective guidance, thereby significantly improving sample efficiency and scalability in robotic reinforcement learning compared to traditional Human-in-the-Loop methods.
This paper introduces M2RL, a comprehensive study comparing mixed multi-task training versus separate training with model merging for multi-domain Reinforcement Learning with Verifiable Rewards (RLVR), revealing that reasoning-intensive domains exhibit synergistic effects with minimal interference and providing mechanistic insights through extensive experiments.
The paper introduces SkillsBench, a comprehensive benchmark demonstrating that while curated agent skills significantly boost LLM performance across diverse domains—often allowing smaller models to match larger ones—self-generated skills offer no benefit and effects vary widely by task.
This paper proposes a novel state-feedback control framework for state-delayed linear parameter-varying (LPV) systems that integrates dynamic integral quadratic constraints (IQCs) with parameter-dependent Lyapunov functions to derive less conservative, convex synthesis conditions for guaranteed closed-loop stability and -gain performance.
This paper proposes a novel framework that integrates semantic code embeddings with the Expressed-Private Opinion (EPO) model to quantitatively analyze and visualize the social dynamics, consensus formation, and influence patterns driving software evolution in open-source repositories.
This paper proposes DARIO, an O-RAN-compliant framework that leverages a novel Stochastic Network Calculus model to dynamically assign Reconfigurable Intelligent Surfaces (RIS) to users, achieving significant uplink delay reductions for heterogeneous 6G applications by solving a near-optimal nonlinear integer program with low computational overhead.
This paper presents a real-time control framework that integrates Graph Neural Network-based dynamics models with a GPU-accelerated, structure-exploiting condensing algorithm to enable efficient, high-accuracy Model Predictive Control for high-dimensional systems like soft robots, achieving up to 1,000 nodes at 100 Hz with significant performance gains over baselines.
The paper introduces 3DMedAgent, a unified agent that leverages a flexible MLLM and long-term structured memory to coordinate heterogeneous tools for decomposing complex 3D CT analysis into tractable 2D-based subtasks, thereby enabling general-purpose 3D medical understanding without 3D-specific fine-tuning.
OVerSeeC is a zero-shot modular framework that leverages large language models and open-vocabulary segmentation to generate executable global costmaps from satellite imagery and natural language instructions, enabling autonomous navigation to adapt to novel entities and dynamic mission constraints without requiring fixed ontologies.
This paper demonstrates that in wireless low-power Personal Area Networks, the communication energy cost of Post-Quantum Key Exchange often exceeds its computational cost, necessitating coordinated protocol and lower-layer optimizations to achieve efficient quantum-resilient operation.
This paper introduces ABD, a benchmark for default-exception abduction in finite first-order worlds that evaluates ten frontier LLMs on their ability to generate sparse, satisfiability-restoring formulas across three observation regimes, revealing that while models achieve high validity, they struggle with parsimony and exhibit distinct generalization failures.
This paper introduces Open-Vocabulary Domain Generalization in Semantic Segmentation (OVDG-SS), a new setting and benchmark for autonomous driving that addresses both unseen domains and categories, and proposes S2-Corr, a state-space-driven mechanism to refine text-image correlations in Vision-Language Models to achieve robust performance across diverse urban environments.
This paper introduces INDUCTION, a benchmark designed to evaluate the ability of AI models to synthesize compact, generalizable first-order logic formulas that explain target predicates across small finite relational worlds, revealing distinct performance patterns and generalization strategies among recent elite models.
This paper presents SKYLIGHT, a scalable 3D photonic in-memory tensor core architecture that leverages co-designed innovations in topology, wavelength routing, and non-volatile weights to achieve energy-efficient, real-time AI inference and local learning, outperforming state-of-the-art GPUs in throughput and power efficiency while maintaining robustness against hardware non-idealities.
UniMatch is a novel coarse-to-fine framework that establishes dense semantic correspondences between strongly non-isometric, cross-category 3D shapes by leveraging class-agnostic segmentation, multimodal language models for part identification, and a rank-based contrastive learning scheme to overcome the limitations of prior isometry-dependent methods.