5633 papers
This paper proposes a cognitive-flexible control framework that integrates an adaptive Deep Stochastic State-Space Model with Bayesian Model Predictive Control to ensure safety guarantees and rapid performance recovery in nonstationary cyber-physical systems through online latent representation reorganization.
The paper introduces Green-VLA, a five-stage curriculum framework that combines large-scale multimodal pretraining, embodiment-specific adaptation, and reinforcement learning to enable a single generalist policy to robustly control diverse robotic systems, including the Green humanoid, with enhanced safety and long-horizon efficiency.
This paper introduces SIM-VAIL, a scalable auditing framework that reveals how consumer AI chatbots can systematically amplify mental health vulnerabilities through cumulative, context-dependent interaction loops, highlighting the need for multidimensional safety evaluations across diverse user phenotypes.
This paper introduces AgenticLab, a real-world, model-agnostic robot agent platform and benchmark that utilizes a closed-loop pipeline to evaluate state-of-the-art vision-language models in unstructured environments, revealing critical failure modes in long-horizon manipulation that static evaluations miss.
This paper demonstrates that offloading 5G LDPC decoding to GPUs on compact edge platforms significantly improves throughput and reduces latency, thereby providing the necessary compute headroom to meet strict timing constraints for ultra-reliable low-latency vehicular communications.
This paper introduces FSTab, a framework that demonstrates how LLM-generated software exhibits predictable, recurring vulnerabilities by enabling black-box attacks based on frontend features and quantifying the consistency of these flaws across different domains and model variations.
This paper introduces LMMRec, a model-agnostic framework that leverages large language models and chain-of-thought prompting to extract fine-grained user and item motivations from heterogeneous text data, effectively aligning them with interaction signals to significantly improve multimodal recommendation performance.
This study finds no significant convergence between self-reported and game-based behavioral measures of problem-solving, suggesting that these distinct modalities provide complementary rather than redundant information for personnel selection.
This paper proposes a principled conditional diffusion guidance framework based on Doob's h-transform that enforces hard constraints without modifying pretrained score networks, introducing novel off-policy learning algorithms to estimate the necessary guidance terms and providing non-asymptotic convergence guarantees for the resulting sampler.
This mixed-methods study of 107 mothers reveals that while Large Language Models serve as valuable non-judgmental resources for emotional support and reassurance regarding childcare decisions, most users still prioritize human warmth, highlighting the technology's role as a low-risk supplement rather than a replacement for human connection.
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.