arXiv:2605.19758v1 Announce Type: new Abstract: The ability to maintain and manipulate information over time is a fundamental aspect of living beings and Artificial Intelligence. While modern models have achieved remarkable success in tasks like natural language processing, evaluating the capacity of novel architectures to process sequential information remains computationally expensive and time-consuming. Testing a new […]
StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs
arXiv:2605.16353v2 Announce Type: replace-cross Abstract: Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models to incrementally acquire new abilities. However, existing CVIT methods operate under a restrictive task-incremental setting, where each training phase corresponds to a single, predefined task. This does not reflect real-world conditions, where data arrives as a continuous stream of interleaved […]
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
arXiv:2605.19769v1 Announce Type: new Abstract: We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection endpoints over real applications, (2) a self-evolving verification layer that improves verifier reliability using execution-grounded feedback, (3) a task-generation pipeline that synthesizes realistic and […]
Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance
arXiv:2605.19355v1 Announce Type: cross Abstract: Retargeting motion across characters with varying body shapes while preserving interaction semantics, such as self-contact and near-body proximity, remains a challenging problem. While recent geometry-aware approaches address this by maintaining spatial relationships between predefined corresponding regions, their reliance on static correspondences often struggles when the target character exhibits exaggerated body […]
Charting an embryological path to cancer cure: A discussion of disease hallmarks
arXiv:2605.19789v1 Announce Type: new Abstract: Embryology has long played a foundational role in shaping our scientific understanding of animal evolution. In recent decades, growing evidence has also highlighted its role in cancer. Despite the indisputable similarities between embryonic development and cancer, there has been limited discussion on the profound embryological implications for the disease. This […]
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
arXiv:2605.15846v2 Announce Type: replace-cross Abstract: Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existing benchmarks focus predominantly on single-issue bug fixes from Python repositories, with coarse pass/fail evaluation outcomes, and thus fail to capture long-horizon, multi-target development at real […]
Streamlined Constraint Reasoning via CNN Pattern Recognition on Enumerated Solutions
arXiv:2605.19895v1 Announce Type: new Abstract: Constraint programming practitioners accelerate hard problems through a layered set of techniques applied in order of risk. Standard hardening (symmetry-breaking and implied constraints) is applied first and preserves satisfiability. Streamliner constraints, which restrict search to a structural sub-family of solutions, do not preserve satisfiability and are reserved as a final […]
PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies
arXiv:2605.19351v1 Announce Type: cross Abstract: Generative agents based on large language models reproduce believable human behavior in cooperative settings, but how they should reason in situations where rule-breaking may be required, such as fire evacuation or authority-supervised emergency, remains poorly characterized. We propose PAVE (Perception, Assessment, Verdict, Emulation), a novel four-module cognitive architecture that addresses […]
Computing the Arc-Deletion Distance to Orchard Networks is NP-hard
arXiv:2605.19962v1 Announce Type: new Abstract: Phylogenetic networks generalize phylogenetic trees by allowing reticulate evolutionary events such as horizontal gene transfer and hybridization. Among the many subclasses of phylogenetic networks, orchard networks have attracted increasing attention due to their structural and algorithmic properties. In this paper, we study the arc-deletion distance to orchard networks, defined as […]
DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
arXiv:2605.15532v2 Announce Type: replace-cross Abstract: Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets. We reveal a critical inefficiency in this approach: up to 69% of the prompts in standard chart / document reasoning datasets are […]
Probing Embodied LLMs: When Higher Observation Fidelity Hurts Problem Solving
arXiv:2605.20072v1 Announce Type: new Abstract: Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or failure in closed-loop embodied tasks. Following an empirical AI methodology, we study embodied LLM agents behaviorally by varying the information available to the agent and measuring […]
IMLJD: A Computational Dataset for Indian Matrimonial Litigation Analysis
arXiv:2605.19346v1 Announce Type: cross Abstract: We present IMLJD, an open dataset of 3,613 Indian court judgments covering matrimonial disputes under IPC Section 498A, the Protection of Women from Domestic Violence Act, and CrPC Section 482. The dataset covers the Supreme Court of India from 2000 to 2024 (1,474 cases) and the Karnataka High Court from […]