arXiv:2608.05341v1 Announce Type: new Abstract: Vision-Language Models (VLMs) for radiology report generation are typically trained on retrospective clinical reports, which suffer from omission noise: clinically present…
arXiv:2608.06366v1 Announce Type: cross Abstract: Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists'…
arXiv:2603.12617v2 Announce Type: replace Abstract: Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model rapidly…
arXiv:2307.12022v3 Announce Type: replace Abstract: Optimizing individualized treatment sequences for patients who weigh multiple, competing outcomes differently poses a challenge for dynamic treatment regime (DTR) methods,…
arXiv:2512.03057v2 Announce Type: replace Abstract: We study distribution-free risk control for model routing, motivated by large language model reasoning. We formalize pointwise conditional efficiency under a…
arXiv:2608.05168v1 Announce Type: new Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures…
arXiv:2604.22191v2 Announce Type: replace-cross Abstract: In agentic workflows, LLMs frequently process retrieved contexts that are legally protected from further training. However, auditors currently lack a reliable…
arXiv:2608.06352v1 Announce Type: cross Abstract: Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes…
arXiv:2506.14243v4 Announce Type: replace Abstract: LiDAR-based place recognition is critical for long-term autonomous driving without GPS. Existing handcrafted feature methods face dual limitations. First, descriptor instability…
arXiv:2608.05250v1 Announce Type: new Abstract: Multi-task supervised fine-tuning (SFT) often casts a heterogeneous data mixture as a single optimization problem, even though different tasks may reach…
arXiv:2608.05358v1 Announce Type: new Abstract: Federated learning repeatedly incurs local optimization and model-update transmission. We study DG-FedReuse, a simulator-level mechanism that allows selected clients to contribute…
arXiv:2608.06337v1 Announce Type: new Abstract: A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one…
arXiv:2608.05454v1 Announce Type: cross Abstract: Probabilistic prediction heads in neural networks typically output either a Gaussian mixture or a single conformal region. Neither separates the distinct…
arXiv:2608.05218v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables fast, photorealistic talking-head rendering, yet accurate lip articulation remains elusive: mouth motion is often over-smoothed and…
arXiv:2608.05876v1 Announce Type: cross Abstract: User requests serve as research specifications for deep research agents, shaping what evidence to seek and how to synthesize it. In…
arXiv:2608.05166v1 Announce Type: new Abstract: We present an evaluation of cognitive bias expression in state-of-the-art instruction-tuned LLMs under realistic multi-turn interaction settings. Our work introduces a…
arXiv:2608.05356v1 Announce Type: new Abstract: High-definition 3D LiDAR maps are important for autonomous driving and smart-city services, which require reliable detection of object-level changes in multi-temporal…
arXiv:2608.05253v1 Announce Type: new Abstract: Quantized orthogonal fine-tuning (qoft) enables parameter-efficient adaptation of low-bit language models by learning structured activation rotations before frozen quantized weights. However,…
arXiv:2607.07144v2 Announce Type: replace Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through…
arXiv:2605.14599v2 Announce Type: replace-cross Abstract: We establish novel structural and statistical results for entropy-regularized min-max inverse reinforcement learning (Min-Max-IRL) in finite-horizon MDPs with Borel state and…
arXiv:2604.21395v3 Announce Type: replace-cross Abstract: Ordinary supervised training minimises the task loss and then stops. It never pays for how far the representation moves when the…
arXiv:2608.05158v1 Announce Type: new Abstract: In biological evolution, unconstrained mutation can lead to catastrophic outcomes: organisms may evolve enhanced capabilities while losing essential functions for survival.…
arXiv:2507.14022v2 Announce Type: replace Abstract: This study proposes the Cognitive Pairwise Comparison Classification Model Selection (CPC-CMS) framework for document-level sentiment analysis. The CPC, based on expert…
arXiv:2604.04444v2 Announce Type: replace Abstract: Open-vocabulary object detection (OVOD) enables models to detect any object category, including unseen ones. Benefiting from large-scale pre-training, existing OVOD methods…