arXiv:2604.06737v2 Announce Type: replace-cross Abstract: Large language models have demonstrated remarkable capabilities across a wide range of natural language processing tasks, yet their application in the legal domain remains challenging due to the specialized terminology, complex reasoning requirements, and rapidly evolving legal knowledge involved. In this paper, we present WisdomInterrogatory (LuWen), an open-source Chinese legal […]
WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models
arXiv:2604.08558v1 Announce Type: cross Abstract: Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed Attention and Knowledge Distillation, a framework that adapts pretrained AR-TTS models to operate with constant computational and memory complexity. […]
Resolving satellite-in situ mismatches in Net Primary Production using high-frequency in situ bio-optical observations in the subpolar Northwest Atlantic
arXiv:2604.08634v1 Announce Type: new Abstract: Net primary productivity (NPP) forms the basis of biological carbon pump, but its estimates in high-latitude regions remain highly uncertain despite its disproportional importance for the global carbon sink. Optical satellites are limited by cloud cover, low irradiance, and shallow light penetration, with uncertainties further exacerbated by the lack of […]
DDSP-QbE++: Improving Speech Quality for Speech Anonymisation for Atypical Speech
arXiv:2604.09246v1 Announce Type: cross Abstract: Differentiable Digital Signal Processing (DDSP) pipelines for voice conversion rely on subtractive synthesis, where a periodic excitation signal is shaped by a learned spectral envelope to reconstruct the target voice. In DDSP-QbE, the excitation is generated via phase accumulation, producing a sawtooth-like waveform whose abrupt discontinuities introduce aliasing artefacts that […]
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
arXiv:2604.09450v1 Announce Type: cross Abstract: Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists’ workload. However, conventional autoregressive vision–language models (VLMs) suffer from high inference latency due to sequential token decoding. Diffusion-based models offer a promising alternative through parallel generation, but they still require multiple denoising iterations. Compressing multi-step denoising to a […]
EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration
arXiv:2512.19396v3 Announce Type: replace Abstract: Contemporary GUI agents, while increasingly capable due to advances in Large Vision-Language Models (VLMs), often operate with a critical limitation: they treat each task in isolation, lacking a mechanism to systematically learn from past successes. This digital ”amnesia” results in sub-optimal performance, repeated errors, and poor generalization to novel challenges. […]
Reflection of Episodes: Learning to Play Game from Expert and Self Experiences
arXiv:2502.13388v4 Announce Type: replace Abstract: StarCraft II is a complex and dynamic real-time strategy (RTS) game environment, which is very suitable for artificial intelligence and reinforcement learning research. To address the problem of Large Language Model(LLM) learning in complex environments through self-reflection, we propose a Reflection of Episodes(ROE) framework based on expert experience and self-experience. […]
Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
arXiv:2505.12509v3 Announce Type: replace-cross Abstract: Post-hoc explanations provide transparency and are essential for guiding model optimization, such as prompt engineering and data sanitation. However, applying model-agnostic techniques to Large Language Models (LLMs) is hindered by prohibitive computational costs, rendering these tools dormant for real-world applications. To revitalize model-agnostic interpretability, we propose a budget-friendly proxy framework […]
Act or Escalate? Evaluating Escalation Behavior in Automation with Language Models
arXiv:2604.08588v1 Announce Type: cross Abstract: Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, estimates its probability of being correct, and compares the expected costs of acting and escalating. Using this framework across five domains of recorded human decisions-demand […]
Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving
arXiv:2603.13842v3 Announce Type: replace-cross Abstract: End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demonstrations. To overcome this limitation, recent methods incorporate reinforcement learning (RL) through sequential fine-tuning. However, such a paradigm remains suboptimal: sequential RL fine-tuning can introduce policy drift and often leads […]
Generalization and Scaling Laws for Mixture-of-Experts Transformers
arXiv:2604.09175v1 Announce Type: cross Abstract: We develop a theory of generalization and scaling for Mixture-of-Experts (MoE) Transformers that cleanly separates emphactive per-input capacity from routing combinatorics. By conditioning on fixed routing patterns and union-bounding across them, we derive a sup-norm covering-number bound whose metric entropy scales with the active parameter budget and incurs a MoE-specific […]
Quantum-like Cognition in Process Theories: An Analysis
arXiv:2604.08604v1 Announce Type: new Abstract: Various effects in human cognition, often considered `non-classical’, have been argued to be most naturally modelled by quantum-like models of decision making. We extend this approach to describe models of cognition and decision-making in general probabilistic process theories, which include both classical probabilistic models and quantum instrument models as special […]