arXiv:2603.06608v1 Announce Type: new Abstract: The research community lacks a middle ground between StarCraft IIs full game and its mini-games. The full-games sprawling state-action space renders reward signals sparse and noisy, but in mini-games simple agents saturate performance. This complexity gap hinders steady curriculum design and prevents researchers from experimenting with modern Reinforcement Learning algorithms […]
PEPA: a Persistently Autonomous Embodied Agent with Personalities
arXiv:2603.00117v2 Announce Type: replace-cross Abstract: Living organisms exhibit persistent autonomy through internally generated goals and self-sustaining behavioral organization, yet current embodied agents remain driven by externally scripted objectives. This dependence on predefined task specifications limits their capacity for long-term deployment in dynamic, unstructured environments where continuous human intervention is impractical. We propose that personality traits […]
SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning
arXiv:2603.08270v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable success across diverse tasks. However, their generalization capability is often hindered by spurious correlations between node features and labels in the graph. Our analysis reveals that GNNs tend to exploit imperceptible statistical correlations in training data, even when such correlations are unreliable for […]
DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention
arXiv:2603.08026v1 Announce Type: cross Abstract: Masked Diffusion Language Models (MDLMs) enable parallel token decoding, providing a promising alternative to the sequential nature of autoregressive generation. However, their iterative denoising process remains computationally expensive because it repeatedly processes the entire sequence at every step. We observe that across these diffusion steps, most token representations remain stable; […]
Amortized Phylodynamic Inference with Neural Bayes Estimators and Recursive Neural Networks
arXiv:2603.08345v1 Announce Type: cross Abstract: Phylodynamics is used to estimate epidemic dynamics from phylogenetic trees or genomic sequences of pathogens, but the likelihood calculations needed can be challenging for complex models. We present a neural Bayes estimator (NBE) for key epidemic quantities: the reproduction number, prevalence, and cumulative infections through time. By performing quantile regression […]
Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments
arXiv:2602.23234v3 Announce Type: replace-cross Abstract: Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for. To maximize relevance, we leverage two complementary objectives: behavioral relevance (results users tend to click or download) and textual relevance (a result’s semantic fit to the query). A persistent challenge […]
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
arXiv:2603.08486v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete and visually depictable, while safety concepts, like helpfulness, are abstract and lack visual referents. Inspired by the Self-Fulfilling mechanism […]
Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model
arXiv:2603.08023v1 Announce Type: cross Abstract: Dance is a form of human motion characterized by emotional expression and communication, playing a role in various fields such as music, virtual reality, and content creation. Existing methods for dance generation often fail to adequately capture the inherently sequential, rhythmical, and music-synchronized characteristics of dance. In this paper, we […]
Scale Space Diffusion
arXiv:2603.08709v1 Announce Type: cross Abstract: Diffusion models degrade images through noise, and reversing this process reveals an information hierarchy across timesteps. Scale-space theory exhibits a similar hierarchy via low-pass filtering. We formalize this connection and show that highly noisy diffusion states contain no more information than small, downsampled images – raising the question of why […]
Autoregressive Visual Decoding from EEG Signals
arXiv:2602.22555v2 Announce Type: replace-cross Abstract: Electroencephalogram (EEG) signals have become a popular medium for decoding visual information due to their cost-effectiveness and high temporal resolution. However, current approaches face significant challenges in bridging the modality gap between EEG and image data. These methods typically rely on complex adaptation processes involving multiple stages, making it hard […]
Let’s Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification
arXiv:2507.11662v3 Announce Type: replace Abstract: Verifiers–functions assigning rewards to agent behavior–have been key to AI progress in math, code, and games. However, extending gains to domains without clear-cut success criteria remains a challenge: while humans can recognize desired outcomes, translating this intuition into scalable rules is nontrivial. Multimodal LLMs (MLLMs) offer a promising solution, given […]
Generalizing matrix representations to fully heterochronous ranked tree shapes
arXiv:2510.27030v4 Announce Type: replace Abstract: Phylogenetic tree shapes capture fundamental signatures of evolution. We consider “ranked” tree shapes, which are equipped with a total order on the internal nodes compatible with the tree graph. Recent work has established an elegant bijection between ranked tree shapes and a class of integer matrices, called textbfF-matrices, defined by […]