arXiv:2603.15159v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown strong potential for code generation, yet they remain limited in private-library-oriented code generation, where the goal is to generate code using APIs from private libraries. Existing approaches mainly rely on retrieving private-library API documentation and injecting relevant knowledge into the context at inference time. […]
Sparse3DTrack: Monocular 3D Object Tracking Using Sparse Supervision
arXiv:2603.18298v1 Announce Type: cross Abstract: Monocular 3D object tracking aims to estimate temporally consistent 3D object poses across video frames, enabling autonomous agents to reason about scene dynamics. However, existing state-of-the-art approaches are fully supervised and rely on dense 3D annotations over long video sequences, which are expensive to obtain and difficult to scale. In […]
REST: Receding Horizon Explorative Steiner Tree for Zero-Shot Object-Goal Navigation
arXiv:2603.18624v1 Announce Type: cross Abstract: Zero-shot object-goal navigation (ZSON) requires navigating unknown environments to find a target object without task-specific training. Prior hierarchical training-free solutions invest in scene understanding (textitbelief) and high-level decision-making (textitpolicy), yet overlook the design of textitoption, i.e., a subgoal candidate proposed from evolving belief and presented to policy for selection. In […]
The Impact of Corporate AI Washing on Farmers’ Digital Financial Behavior Response — An Analysis from the Perspective of Digital Financial Exclusion
arXiv:2603.18421v1 Announce Type: cross Abstract: In the context of the rapid development of digital finance, some financial technology companies exhibit the phenomenon of “AI washing,” where they overstate their AI capabilities while underinvesting in actual AI resources. This paper constructs a corporate-level AI washing index based on CHFS2019 data and AI investment data from 15-20 […]
AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Agents
arXiv:2603.12564v2 Announce Type: replace-cross Abstract: Tool-augmented LLM agents increasingly serve as multi-turn advisors in high-stakes domains, yet their evaluation relies on ranking-quality metrics that measure what is recommended but not whether it is safe for the user. We introduce a paired-trajectory protocol that replays real financial dialogues under clean and contaminated tool-output conditions across seven […]
Implicit Patterns in LLM-Based Binary Analysis
arXiv:2603.19138v1 Announce Type: new Abstract: Binary vulnerability analysis is increasingly performed by LLM-based agents in an iterative, multi-pass manner, with the model as the core decision-maker. However, how such systems organize exploration over hundreds of reasoning steps remains poorly understood, due to limited context windows and implicit token-level behaviors. We present the first large-scale, trace-level […]
OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data
arXiv:2603.18623v1 Announce Type: cross Abstract: Text-to-motion (T2M) generation aims to create realistic human movements from text descriptions, with promising applications in animation and robotics. Despite recent progress, current T2M models perform poorly on unseen text descriptions due to the small scale and limited diversity of existing motion datasets. To address this problem, we introduce OpenT2M, […]
How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding
arXiv:2603.18009v1 Announce Type: cross Abstract: With the widespread adoption of large language models (LLMs) in natural language processing, prompt engineering and retrieval-augmented generation (RAG) have become mainstream to enhance LLMs’ performance on complex tasks. However, LLMs generate outputs autoregressively, leading to inevitable output uncertainty. Since model performance is highly sensitive to prompt design, precise uncertainty […]
Affect Decoding in Phonated and Silent Speech Production from Surface EMG
arXiv:2603.11715v2 Announce Type: replace-cross Abstract: The expression of affect is integral to spoken communication, yet, its link to underlying articulatory execution remains unclear. Measures of articulatory muscle activity such as EMG could reveal how speech production is modulated by emotion alongside acoustic speech analyses. We investigate affect decoding from facial and neck surface electromyography (sEMG) […]
ProKWS: Personalized Keyword Spotting via Collaborative Learning of Phonemes and Prosody
arXiv:2603.18024v1 Announce Type: cross Abstract: Current keyword spotting systems primarily use phoneme-level matching to distinguish confusable words but ignore user-specific pronunciation traits like prosody (intonation, stress, rhythm). This paper presents ProKWS, a novel framework integrating fine-grained phoneme learning with personalized prosody modeling. We design a dual-stream encoder where one stream derives robust phonemic representations through […]
Learning to Self-Evolve
arXiv:2603.18620v1 Announce Type: cross Abstract: We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE in the setting of test-time self-evolution, where a model iteratively refines its context from feedback on seen problems to perform better on new […]
Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems
arXiv:2603.18034v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems extend large language models (LLMs) with external knowledge sources but introduce new attack surfaces through the retrieval pipeline. In particular, adversaries can poison retrieval corpora so that malicious documents are preferentially retrieved at inference time, enabling targeted manipulation of model outputs. We study gradient-guided corpus poisoning […]