arXiv:2601.06160v2 Announce Type: replace Abstract: Large Language Models (LLMs) often suffer from ”Reasoning Collapse” on challenging mathematical reasoning tasks, where stochastic sampling produces lexical variations of the same erroneous logic rather than genuine semantic exploration. We observe that failed reasoning traces are often associated with a low-rank bias manifold in the model’s hidden-state geometry, which […]
Domain-Adapted Small Language Models for Reliable Clinical Triage
arXiv:2604.26766v1 Announce Type: cross Abstract: Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent challenge in emergency departments, where highly variable free-text triage documentation contributes to mistriage and workflow inefficiencies. This study evaluates whether open-source small language models (SLMs) can serve as reliable, privacy-preserving decision-support tools for clinical triage. We systematically compared multiple […]
A Framework for Longitudinal Health AI Agents
arXiv:2604.12019v3 Announce Type: replace Abstract: Although artificial intelligence (AI) agents are increasingly proposed to support potentially longitudinal health tasks, such as symptom management, behavior change, and patient support, most current implementations fall short of facilitating user intent and fostering accountability. This contrasts with prior work on supporting longitudinal needs, both within and beyond clinical settings, […]
Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion
arXiv:2604.16552v2 Announce Type: replace-cross Abstract: Recent text-to-scene generation approaches largely reduced the manual efforts required to create 3D scenes. However, their focus is either to generate a scene layout or to generate objects, and few generate both. The generated scene layout is often simple even with LLM’s help. Moreover, the generated scene is often inconsistent […]
Identifying the Achilles’ Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models
arXiv:2401.00761v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) like ChatGPT are foundational in various applications due to their extensive knowledge from pre-training and fine-tuning. Despite this, they are prone to generating factual and commonsense errors, raising concerns in critical areas like healthcare, journalism, and education to mislead users. Current methods for evaluating LLMs’ veracity […]
Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework
arXiv:2604.26762v1 Announce Type: cross Abstract: The Probabilistic Transformer (PT) establishes that the Transformer’s self-attention plus its feed-forward block is mathematically equivalent to Mean-Field Variational Inference (MFVI) on a Conditional Random Field (CRF). Under this equivalence the Transformer ceases to be a black-box neural network and becomes a programmable factor graph: graph topology, factor potentials, and […]
M2R2: MultiModal Robotic Representation for Temporal Action Segmentation
arXiv:2504.18662v3 Announce Type: replace-cross Abstract: Temporal action segmentation (TAS) has long been a key area of research in both robotics and computer vision. In robotics, algorithms have primarily focused on leveraging proprioceptive information to determine skill boundaries, with recent approaches in surgical robotics incorporating vision. In contrast, computer vision typically relies on exteroceptive sensors, such […]
Awakening Dormant Experts:Counterfactual Routing to Mitigate MoE Hallucinations
arXiv:2604.14246v2 Announce Type: replace-cross Abstract: Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to hallucinations, particularly when processing long-tail knowledge. We identify that this fragility stems from static Top-$k$ routing: routers tend to favor high-frequency patterns over rare factual associations. Consequently, “specialist experts” possessing critical long-tail knowledge are often assigned low […]
MINOS: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text
arXiv:2506.02494v2 Announce Type: replace-cross Abstract: Evaluation is important for multimodal generation tasks, while traditional multimodal evaluation metrics suffer from several limitations. With the rapid progress of MLLMs, there is growing interest in applying MLLMs to build general evaluation systems. However, existing researches often simply collect large-scale evaluation data for training, while overlooking the quality of […]
A self-evolving agent for explainable diagnosis of DFT-experiment band-gap mismatch
arXiv:2604.26703v1 Announce Type: cross Abstract: Standard density functional theory (DFT) routinely misclassifies the electronic ground state of correlated and structurally complex compounds, predicting metallic behaviour for materials that experiments report as semiconductors. Each such mismatch encodes a specific non-ideality — magnetic ordering, electron correlation, an alternative polymorph, or a defect — that the calculation excluded, […]
Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
arXiv:2508.12672v4 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wherein FL clients are subject to adversarial (Byzantine) attacks, while the FL server is trusted (honest) and has a trustworthy side dataset. This may correspond to, e.g., cases where the server possesses […]
Graph Propagated Projection Unlearning: A Unified Framework for Vision and Audio Discriminative Models
arXiv:2604.13127v2 Announce Type: replace-cross Abstract: The need to selectively and efficiently erase learned information from deep neural networks is becoming increasingly important for privacy, regulatory compliance, and adaptive system design. We introduce Graph-Propagated Projection Unlearning (GPPU), a unified and scalable algorithm for class-level unlearning that operates across both vision and audio models. GPPU employs graph-based […]