arXiv:2604.04843v1 Announce Type: cross Abstract: Human-object-scene interactions (HOSI) generation has broad applications in embodied AI, simulation, and animation. Unlike human-object interaction (HOI) and human-scene interaction (HSI), HOSI generation requires reasoning over dynamic object-scene changes, yet suffers from limited annotated data. To address these issues, we propose a coarse-to-fine instruction-conditioned interaction generation framework that is explicitly […]
Gray Anchoring: a New Computational Theory for Biological Color Constancy
arXiv:2410.08823v3 Announce Type: replace Abstract: It is still challenging for computer vision to imitate human color perception, e.g., color constancy, which is a fundamental perceptual ability in humans to perceive, interpret and interact with their surroundings. Among others, the anchoring theory provides impressive insights for human lightness perception, yet the specific anchoring rules underlying color […]
Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows
arXiv:2512.13168v4 Announce Type: replace Abstract: We introduce FinWorkBench (a.k.a. Finch), a benchmark for evaluating agents on real-world, enterprise-grade finance and accounting workflows that interleave data entry, structuring, formatting, web search, cross-file retrieval, calculation, modeling, validation, translation, visualization, and reporting. Finch is built from authentic enterprise workspaces from Enron (15,000 files and 500,000 emails) and other […]
Collective AI can amplify tiny perturbations into divergent decisions
arXiv:2603.09127v2 Announce Type: replace Abstract: Large language models are increasingly deployed not as single assistants but as committees whose members deliberate and then vote or synthesize a decision. Such systems are often expected to be more robust than individual models. We show that iterative multi-LLM deliberation can instead amplify tiny perturbations into divergent conversational trajectories […]
SPRIG: Improving Large Language Model Performance by System Prompt Optimization
arXiv:2410.14826v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown impressive capabilities in many scenarios, but their performance depends, in part, on the choice of prompt. Past research has focused on optimizing prompts specific to a task. However, much less attention has been given to optimizing the general instructions included in a prompt, known […]
VERDI: VLM-Embedded Reasoning for Autonomous Driving
arXiv:2505.15925v4 Announce Type: replace-cross Abstract: While autonomous driving (AD) stacks struggle with decision making under partial observability and real-world complexity, human drivers are capable of applying commonsense reasoning to make near-optimal decisions with limited information. Recent work has attempted to leverage finetuned Vision-Language Models (VLMs) for trajectory planning at inference time to emulate human behavior. […]
DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
arXiv:2509.12626v3 Announce Type: replace-cross Abstract: Aligning agentic AI with user intent is critical for delegating complex, socially embedded tasks, yet user preferences are often implicit, evolving, and difficult to specify upfront. We present DoubleAgents, a system for human-agent alignment in coordination tasks, grounded in distributed cognition. DoubleAgents integrates three components: (1) a coordination agent that […]
ATLAS: A Layered Constraint-Guided Framework for Structured Artifact Generation in LLM-Assisted MDE
arXiv:2510.25890v3 Announce Type: replace-cross Abstract: ATLAS is a constraint-guided generation framework for structured engineering artifacts whose outputs must satisfy explicit schemas, domain rules, and audit requirements. Rather than treating a large language model as a standalone generator, ATLAS places generation inside a model-driven workflow that separates domain representation, constraint compilation, and post-generation validation. ATLAS combines […]
The Malignant Tail: Spectral Segregation of Label Noise in Over-Parameterized Networks
arXiv:2603.02293v2 Announce Type: replace-cross Abstract: While implicit regularization facilitates benign overfitting in low-noise regimes, recent theoretical work predicts a sharp phase transition to harmful overfitting as the noise-to-signal ratio increases. We experimentally isolate the geometric mechanism of this transition: the Malignant Tail, a failure mode where networks functionally segregate signal and noise, reducing coherent semantic […]
FAST-CAD: A Fairness-Aware Framework for Non-Contact Stroke Diagnosis
arXiv:2511.08887v4 Announce Type: replace-cross Abstract: Stroke is an acute cerebrovascular disease, and timely diagnosis significantly improves patient survival. However, existing automated diagnosis methods suffer from fairness issues across demographic groups, potentially exacerbating healthcare disparities. In this work we propose FAST-CAD, a theoretically grounded framework that combines domain-adversarial training (DAT) with group distributionally robust optimization (Group-DRO) […]
LLMs Judging LLMs: A Simplex Perspective
arXiv:2505.21972v3 Announce Type: replace-cross Abstract: Given the challenge of automatically evaluating free-form outputs from large language models (LLMs), an increasingly common solution is to use LLMs themselves as the judging mechanism, without any gold-standard scores. Implicitly, this practice accounts for only sampling variability (aleatoric uncertainty) and ignores uncertainty about judge quality (epistemic uncertainty). While this […]
An Onto-Relational-Sophic Framework for Governing Synthetic Minds
arXiv:2603.18633v2 Announce Type: replace Abstract: The rapid evolution of artificial intelligence, from task-specific systems to foundation models exhibiting broad, flexible competence across reasoning, creative synthesis, and social interaction, has outpaced the conceptual and governance frameworks designed to manage it. Current regulatory paradigms, anchored in a tool-centric worldview, address algorithmic bias and transparency but leave unanswered […]