1187419 results (page 90 of 47497)
-
FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
Federated fine-tuning of Large Language Models (LLMs) is obstructed by a trilemma of challenges: protecting LLMs intellectual property (IP), ensuring client privacy, and mitigating performance loss on heterogeneous data. Existing methods like Offsite-Tuning (OT) secure the LLMs IP by having clients train only lightweight adapters, yet our analysis reveals they suffer from a fundamental performance…
-
Quantitative Verification of Finite-Time Constrained Occupation Measures for Continuous-time Stochastic Systems
This paper addresses the quantitative verification of finite-time constrained occupation time for stochastic continuous-time systems governed by stochastic differential equations (SDEs). Unlike classical reachability analysis, which focuses on single-event properties such as entering a target set, many autonomous tasks-including surveillance, wireless charging, and chemical mixing-require a system…
-
Security Is Relative: Training-Free Vulnerability Detection via Multi-Agent Behavioral Contract Synthesis
Deep learning for vulnerability detection has shown promising results on early benchmarks, but recent evaluations reveal catastrophic degradation: models achieving F1 > 0.68 on legacy datasets collapse to 0.031 under strict deduplication. We identify the root cause as the semantic ambiguity problem: identical code can be secure or vulnerable depending on project-specific behavioral contracts, rend…
-
Accelerating trajectory optimization with Sobolev-trained diffusion policies
Trajectory Optimization (TO) solvers exploit known system dynamics to compute locally optimal trajectories through iterative improvements. A downside is that each new problem instance is solved independently; therefore, convergence speed and quality of the solution found depend on the initial trajectory proposed. To improve efficiency, a natural approach is to warm-start TO with initial guesses pr…
-
SSB-Based Sensing-Assisted Robust Beamforming for High-Mobility UAV Communications in LAWN
High-mobility uncrewed aerial vehicle (UAV) communications in low-altitude wireless networks (LAWN) demand reliable beamforming, while conventional feedback-based schemes suffer from excessive overhead and severe misalignment under rapid trajectory variations. To address this challenge, this paper proposes an SSB-based sensing-assisted predictive robust beamforming framework that replaces explicit…
-
Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning
Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation offers potential, a naive fusion of these two objectives relies on suboptimal raw sample evaluation. This sample-based scoring creates inherent conflicts with …
-
Optimal Online and Offline Algorithms for Contextual MNL with Applications to Assortment and Pricing
Selecting which products to display and at what prices is a central decision in retail and e-commerce operations. In many applications, these two choices must be made jointly under limited display capacity and uncertain customer demand. In this paper, we study the joint assortment and pricing problem under a price-based contextual multinomial logit model, where customer preferences depend on both …
-
ExplainS2A: Explainable Spectral-Spatial Duality Model for Fast Transforming Sentinel-2 Image to AVIRIS-Level Hyperspectral Image
Mainstream optical satellites often acquire multispectral multi-resolution images, which have limited material identifiability compared to the HSIs. Thus, spectrally super-resolving the MSI into their hyperspectral counterparts greatly facilitates remote material identification and the downstream tasks. However, spectrally super-resolving the MSI into an HSI is often constrained by the multi-resol…
-
Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only about what is said, but also about what is left unsaid. We propose RADAR, a role-anchored multi-agent debate framework for omission-aware fact verification unde…
-
Ocean: Fast Estimation-Based Sparse General Matrix-Matrix Multiplication on GPU
In computational science and data analytics, many workloads involve irregular and sparse computations that are inherently difficult to optimize for modern hardware. A key kernel is Sparse General Matrix-Matrix Multiplication (SpGEMM), which underpins simulations, graph analytics, and machine learning applications. SpGEMM exhibits irregular memory access patterns and workload imbalance, making it c…
-
When Safety Fails Before the Answer: Benchmarking Harmful Behavior Detection in Reasoning Chains
Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. When jailbroken, harm does not appear instantaneously but unfolds through distinct behavioral steps such as suppressing refusal, rationalizing compliance, decomposing harmful tasks, and concealing risk. However, no existi…
-
Decompose, Structure, and Repair: A Neuro-Symbolic Framework for Autoformalization via Operator Trees
Statement autoformalization acts as a critical bridge between human mathematics and formal mathematics by translating natural language problems into formal language. While prior works have focused on data synthesis and diverse training paradigms to optimize end-to-end Large Language Models (LLMs), they typically treat formal code as flat sequences, neglecting the hierarchical logic inherent in mat…
-
A Data-embedded Solution Paradigm for Nonconvex Probable Event Constrained Optimization
This paper introduces a new modeling framework for optimization under uncertainty, called Probable Event Constrained Optimization (PECO). Unlike conventional chance-constrained formulations, which only limit the probability of constraint violation, PECO also explicitly requires feasibility for all events whose probability exceeds a prescribed threshold. This guarantees that solutions remain valid …
-
$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits deployment. In this work, we observe that a substantial part of this inefficiency comes from recurring redundancy in the decoding process, including spatial redund…
-
AutoAWG: Adverse Weather Generation with Adaptive Multi-Controls for Automotive Videos
Perception robustness under adverse weather remains a critical challenge for autonomous driving, with the core bottleneck being the scarcity of real-world video data in adverse weather. Existing weather generation approaches struggle to balance visual quality and annotation reusability. We present AutoAWG, a controllable Adverse Weather video Generation framework for Autonomous driving. Our method…
-
Estimating galactic foreground with the population of resolved galactic binaries
The stochastic gravitational wave background in the mHz band is a key target for future spaceborne interferometers. Detecting such a signal presents multiple challenges for data processing, especially complicated by the presence of numerous compact binaries in our galaxy. The superposition of gravitational waves from their inspiral stages creates a confusion foreground that need to be estimated ac…
-
A Multi-Agent Framework with Structured Reasoning and Reflective Refinement for Multimodal Empathetic Response Generation
Multimodal empathetic response generation (MERG) aims to generate emotionally engaging and empathetic responses based on users' multimodal contexts. Existing approaches usually rely on an implicit one-pass generation paradigm from multimodal context to the final response, which overlooks two intrinsic characteristics of MERG: (1) Human perception of emotional cues is inherently structured rather t…
-
Inertia Matching Principle: Improving Transient Synchronization Stability in Hybrid Power Systems With VSGs and SGs
This paper investigates the transient synchronization stability in power systems hybridized with virtual synchronous generators (VSGs) and synchronous generators (SGs). A relative swing equation model is established to capture the transient synchronization dynamics between the VSG and the SG. Based on this model, both static and dynamic characteristics are systematically analyzed, and a quantitati…
-
A Tight Channel-Capacity Lower Bound for the Simultaneous Wireless Information and Power Transfer Integrated Receiver
Contrary to the vast majority of works on simultaneous wireless information and power transfer that provide information-theoretic limits for the separate receiver architecture, in this work we focus on the integrated receiver and provide a channel-capacity lower bound. Towards this, we provide a closed-form tight approximation for the probability transition matrix of the channel by leveraging the …
-
The Gamma-Ray Monitor onboard the SVOM satellite
The Gamma-Ray Monitor (GRM) is a key scientific payload onboard the Space-based Multi-band Variable Object Monitor (SVOM) satellite, designed specifically for the detection and study of gamma-ray bursts (GRBs). Launched into a 625 km low-Earth orbit on 22 June 2024, GRM serves as a large-area, wide-field-of-view instrument capable of observing the hard X-ray and soft gamma-ray emissions in the ene…
-
SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution
Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents. Training such agents via reinforcement learning requires solving the credit assignment problem: determining how individual utterances contribute to multi-turn dialogue outcomes. Existing approaches directly employ language models to distribute episode-level rewards…
-
AdaGScale: Viewpoint-Adaptive Gaussian Scaling in 3D Gaussian Splatting to Reduce Gaussian-Tile Pairs
Reducing the number of Gaussian-tile pairs is one of the most promising approaches to improve 3D Gaussian Splatting (3D-GS) rendering speed on GPUs. However, the importance difference existing among Gaussian-tile pairs has never been considered in the previous works. In this paper, we propose AdaGScale, a novel viewpoint-adaptive Gaussian scaling technique for reducing the number of Gaussian-tile …
-
Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
Scaling critic capacity is a promising direction for enhancing off-policy reinforcement learning (RL). However, larger critics are prone to overfitting and unstable in replay-buffer-based bootstrap training. This paper leverages Low-Rank Adaptation (LoRA) as a structural-sparsity regularizer for off-policy critics. Our approach freezes randomly initialized base matrices and solely optimizes low-ra…
-
STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming
While Large Language Models (LLMs) are widely used, they remain susceptible to jailbreak prompts that can elicit harmful or inappropriate responses. This paper introduces STAR-Teaming, a novel black-box framework for automated red teaming that effectively generates such prompts. STAR-Teaming integrates a Multi-Agent System (MAS) with a Strategy-Response Multiplex Network and employs network-driven…
-
Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game
In long-horizon open-world multi-agent systems, existing methods often treat local anomalies as automatic triggers for communication. This default design introduces coordination noise, interrupts local execution, and overuses public interaction in cases that could be resolved locally. To address this issue, we propose a partitioned information architecture for MLLM agents that explicitly separates…