arXiv:2604.02816v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and memory costs hinder deployment in resource-constrained settings. While Post-Training Quantization (PTQ) and vision token pruning are standard compression techniques, they are usually treated as independent optimizations. In this paper, we show that these two techniques […]
Spatial-Aware Conditioned Fusion for Audio-Visual Navigation
arXiv:2604.02390v1 Announce Type: cross Abstract: Audio-visual navigation tasks require agents to locate and navigate toward continuously vocalizing targets using only visual observations and acoustic cues. However, existing methods mainly rely on simple feature concatenation or late fusion, and lack an explicit discrete representation of the target’s relative position, which limits learning efficiency and generalization. We […]
AutiHero: Engaging Parents in Creating Personalized, Multi-path Social Narratives for Autistic Children
arXiv:2509.17608v3 Announce Type: replace-cross Abstract: Social narratives help autistic children understand and navigate social situations through stories. To ensure effective practice, however, they often require significant time and effort from parents in customizing the narrative materials and delivering repeated instructions on them. We present AutiHero, a generative AI (GenAI)-based social narrative system, which supports parents […]
Discovery of Bimodal Drift Rate Structure in FRB 20240114A: Evidence for Dual Emission Regions
arXiv:2603.18109v2 Announce Type: replace-cross Abstract: We report the discovery of bimodal structure in the drift rate distribution of upward-drifting burst clusters from the hyperactive repeating fast radio burst FRB 20240114A. Using unsupervised machine learning (UMAP dimensionality reduction combined with HDBSCAN density-based clustering) applied to 233 upward-drifting burst clusters from the FAST telescope dataset, we identify […]
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
arXiv:2511.02734v2 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability. This neglects a crucial capability: agents’ ability to devise and adjust cost-optimal plans in response to changing environments. To bridge this gap, we introduce CostBench, a scalable, cost-centric benchmark designed to evaluate […]
Efficient Causal Graph Discovery Using Large Language Models
arXiv:2402.01207v5 Announce Type: replace-cross Abstract: We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-based methods have used a pairwise query approach, this requires a quadratic number of queries which quickly becomes impractical for larger causal graphs. In contrast, the proposed framework uses a breadth-first search (BFS) approach which […]
Assessing High-Risk AI Systems under the EU AI Act: From Legal Requirements to Technical Verification
arXiv:2512.13907v3 Announce Type: replace-cross Abstract: The implementation of the AI Act requires practical mechanisms to verify compliance with legal obligations, yet concrete and operational mappings from high-level requirements to verifiable assessment activities remain limited, contributing to uneven readiness across Member States. This paper presents a structured mapping that translates high-level AI Act requirements into concrete, […]
A Systematic Security Evaluation of OpenClaw and Its Variants
arXiv:2604.03131v1 Announce Type: cross Abstract: Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic security assessment of six representative OpenClaw-series agent frameworks, namely OpenClaw, AutoClaw, QClaw, KimiClaw, MaxClaw, and ArkClaw, under multiple […]
annbatch unlocks terabyte-scale training of biological data in anndata
arXiv:2604.01949v2 Announce Type: replace-cross Abstract: The scale of biological datasets now routinely exceeds system memory, making data access rather than model computation the primary bottleneck in training machine-learning models. This bottleneck is particularly acute in biology, where widely used community data formats must support heterogeneous metadata, sparse and dense assays, and downstream analysis within established […]
FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation
arXiv:2512.18809v2 Announce Type: replace-cross Abstract: Short-form video moderation increasingly needs learning pipelines that protect user privacy without paying the full bandwidth and latency cost of cloud-centralized inference. We present FedVideoMAE, an on-device federated framework for video violence detection that combines self-supervised VideoMAE representations, LoRA-based parameter-efficient adaptation, client-side DP-SGD, and server-side secure aggregation. By updating only […]
Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models
arXiv:2603.17677v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge into language model generation. However, when retrieved context is noisy, unreliable, or inconsistent with the model’s parametric knowledge, it introduces retrieval-prior conflicts that can degrade generation quality. While this problem has been studied in autoregressive language models, it remains largely […]
How Annotation Trains Annotators: Competence Development in Social Influence Recognition
arXiv:2604.02951v1 Announce Type: cross Abstract: Human data annotation, especially when involving experts, is often treated as an objective reference. However, many annotation tasks are inherently subjective, and annotators’ judgments may evolve over time. This study investigates changes in the quality of annotators’ work from a competence perspective during a process of social influence recognition. The […]