arXiv:2605.06669v2 Announce Type: replace-cross Abstract: Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting, showing that guardrail design entails explicit trade-offs among adversarial robustness, benign-task usability, and response latency. We evaluate a […]
IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation
arXiv:2605.16258v2 Announce Type: replace-cross Abstract: Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundation models predict explicit geometry by regressing pixel-aligned pointmaps, often suffering from redundancy and limited geometric continuity. We propose IVGT, an Implicit Visual Geometry Transformer that implicitly […]
Towards Clinically Interpretable Ophthalmic VQA via Spatially-Grounded Lesion Evidence
arXiv:2605.22414v1 Announce Type: cross Abstract: Visual Question Answering (VQA) holds great promise for clinical support, particularly in ophthalmology, where retinal fundus photography is essential for diagnosis. However, ophthalmic VQA benchmarks primarily emphasize answer accuracy, neglecting the explicit visual evidence necessary for clinical interpretability. In this work, we introduce FundusGround, a new benchmark for clinically interpretable […]
Bernini: Latent Semantic Planning for Video Diffusion
arXiv:2605.22344v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) and diffusion models have each reached remarkable maturity: MLLMs excel at reasoning over heterogeneous multimodal inputs with strong semantic grounding, while diffusion models synthesize images and videos with photorealistic fidelity. We argue that these two families can be unified through a simple division of labor: […]
Dynamic Hypergraph Representation Learning for Multivariate Time Series without Prior Knowledge
arXiv:2605.22540v1 Announce Type: cross Abstract: Hypergraphs have the capacity to capture higher-dimensional relationships among entities across various domains, making them a subject of growing interest within the research community for understanding the structure and dynamics of complex systems. However, a key challenge is the derivation of hypergraph representations from time series data in situations where […]
Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators
arXiv:2605.22343v1 Announce Type: cross Abstract: Autonomous research systems increasingly make the scientific workflow executable: agents can propose ideas, run code, inspect results, and draft papers. But executable workflows do not by themselves produce research judgment. We analyze where current systems lose trial experience: weak evidence becomes prose, pilot signals become broad claims, memory remains textual, […]
Vector Policy Optimization: Training for Diversity Improves Test-Time Search
arXiv:2605.22817v1 Announce Type: cross Abstract: Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select rollouts with a variety of task-specific reward functions. Unfortunately, the standard paradigm of LLM post-training optimizes a pre-specified scalar reward, often leading current LLMs to produce low-entropy […]
Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action
arXiv:2605.15153v2 Announce Type: replace-cross Abstract: We present Pelican-Unify 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unify 1.0 uses a single VLM as a unified understanding module, mapping scenes, instructions, visual contexts, and action histories into a shared semantic space. The same VLM also serves as a unified reasoning module, […]
Understanding Persuasion in Long-Running Agents
arXiv:2602.00851v3 Announce Type: replace Abstract: Modern AI agents increasingly combine conversational interaction with autonomous task execution, such as coding and web research, raising a natural question: What happens when an agent engaged in long-horizon tasks is exposed to user persuasion? Yet studying this possibility is challenging because long-running agent behavior is noisy and costly to […]
4D-GSW: Kinematic-Aware Spatio-Temporal Consistent Watermarking for 4D Gaussian Splatting
arXiv:2605.22342v1 Announce Type: cross Abstract: While 4D Gaussian Splatting (4DGS) has revolutionized high-fidelity dynamic reconstruction, safeguarding the intellectual property of these assets remains an open challenge. Conventional steganographic techniques often neglect the underlying kinematic manifolds, triggering non-physical artifacts such as severe temporal flickering and “FVD collapse”. To address this, we propose textbf4D-GSW, a kinematic-aware watermarking […]
Beyond the Black Box: Interpretability of Agentic AI Tool Use
arXiv:2605.06890v2 Announce Type: replace Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control. Agents may skip required tool calls, invoke tools unnecessarily, or take actions whose consequence becomes visible only after execution. Existing observability methods are mostly external: prompts reveal correlations, […]
Holder Policy Optimisation
arXiv:2605.12058v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mapping these trajectory-level advantages to policy updates requires aggregating token-level probabilities within each sequence. Relying on a fixed aggregation mechanism for this step fundamentally limits the algorithm’s adaptability. Empirically, we observe […]