arXiv:2605.05966v1 Announce Type: new Abstract: Multiple stable states – the coexistence of two or more distinct ecological configurations under identical environmental conditions – have attracted sustained interest in ecology, yet the field still lacks a unified framework connecting ecological mechanisms to dynamical models. Here, we review empirical and theoretical approaches to multiple stable states, synthesising […]
Enhancing Speaker Verification with Whispered Speech via Post-Processing
arXiv:2604.20229v2 Announce Type: replace-cross Abstract: Speaker verification is a task of confirming an individual’s identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification systems in real-life scenarios, including avoiding fully phonated speech to protect privacy, disrupt others, or when the lack […]
Strat-LLM: Stratified Strategy Alignment for LLM-based Stock Trading with Real-time Multi-Source Signals
arXiv:2605.06024v1 Announce Type: new Abstract: Large Language Models (LLMs) are evolving into autonomous trading agents, yet existing benchmarks often overlook the interplay between architectural reasoning and strategy consistency. We propose Strat-LLM, a framework grounded in Stratified Strategy Alignment. Operating in a live-forward setting throughout 2025, it integrates heterogeneous data including sequential prices, real-time news, and […]
TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models
arXiv:2605.06047v1 Announce Type: cross Abstract: Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance through in-context learning, but their inductive biases remain fixed at inference time. Adapting a pretrained TFM to a specific dataset or task typically requires either full fine-tuning, which is computationally expensive, or parameter-efficient […]
VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?
arXiv:2605.06068v1 Announce Type: new Abstract: For years, we have built LLM serving systems like any other critical infrastructure: a single general-purpose stack, hand-tuned over many engineer-years, meant to support every model and workload. In this paper, we take the opposite bet: a multi-agent loop that automatically synthesizes bespoke serving systems for different usage scenarios. We […]
Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
arXiv:2604.18978v2 Announce Type: replace-cross Abstract: Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this paper, we propose using Low-Rank Adaptation (LoRA) as a structural regularizer for critic learning. Our approach freezes randomly […]
CrossCult-KIBench: A Benchmark for Cross-Cultural Knowledge Insertion in MLLMs
arXiv:2605.06115v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs), trained primarily on English-centric data, frequently generate culturally inappropriate or misaligned responses in cross-cultural settings. To mitigate this, we introduce the task of cross-cultural knowledge insertion, which focuses on adapting models to specific cultural contexts while preserving their original behavior in other cultures. To facilitate […]
Optimal Transport for LLM Reward Modeling from Noisy Preference
arXiv:2605.06036v1 Announce Type: cross Abstract: Reward models are fundamental to Reinforcement Learning from Human Feedback (RLHF), yet real-world datasets are inevitably corrupted by noisy preference. Conventional training objectives tend to overfit these errors, while existing denoising approaches often rely on homogeneous noise assumptions that fail to capture the complexity of linguistic preferences. To handle these […]
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
arXiv:2605.06130v1 Announce Type: new Abstract: A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and distills new skills from experience. Existing methods optimize these capabilities in isolation or with separate reward sources, […]
Latent Abstraction for Retrieval-Augmented Generation
arXiv:2604.17866v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has become a standard approach for enhancing large language models (LLMs) with external knowledge, mitigating hallucinations, and improving factuality. However, existing systems rely on generating natural language queries at each hop and maintaining a strict architectural separation between retriever and generator, preventing them from leveraging the full […]
BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents
arXiv:2605.06177v1 Announce Type: new Abstract: Building a deep research agent today is an exercise in glue code: the same backbone evaluated on the same benchmark can report different accuracies in different papers because harness and tool registry all differ, and integrating a new foundation model into a comparable evaluation surface costs weeks of model-specific engineering. […]
Quantum Kernels for Audio Deepfake Detection Using Spectrogram Patch Features
arXiv:2605.06035v1 Announce Type: cross Abstract: Quantum machine learning has emerged as a promising tool for pattern recognition, yet many audio-focused approaches still treat spectrograms as generic images and do not explicitly exploit their time-frequency structure. We propose Q-Patch, a quantum feature map tailored to audio that encodes local time-frequency patches from mel-spectrograms into quantum states […]