arXiv:2605.23122v1 Announce Type: new Abstract: Digital twins of sensory cortex serve as powerful response oracles. Although prediction accuracy is the central metric by which these models are evaluated, it provides limited insight into the latent representations that support those predictions. This becomes increasingly important as digital twins are used as in silico experimental systems for […]
When Good Equations Get Bad Scores: Improving Symbolic Regression Through Better Parameter Optimization
arXiv:2605.23272v1 Announce Type: cross Abstract: Symbolic Regression (SR) plays a central role in scientific knowledge discovery by distilling mathematical equations from observational data. Most existing SR methods function within a bi-level optimization framework: an outer loop that searches for the discrete equation structure, and an inner loop that optimizes the continuous parameters of that structure. […]
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
arXiv:2605.05704v2 Announce Type: replace-cross Abstract: Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilities unlock substantial practical value, they also introduce new security risks, as adversaries can manipulate agents into performing harmful actions in real-world environments. Existing defense strategies mitigate […]
CHASD: Language Increment-Calibrated Contrastive Decoding against Hallucination in LVLMs
arXiv:2605.23344v1 Announce Type: cross Abstract: Large Vision-Language Models have shown strong multimodal reasoning capabilities, yet they remain susceptible to object hallucinations when language priors dominate insufficient or misaligned visual evidence. Training-free contrastive decoding methods mitigate this issue by comparing predictions from original and perturbed visual inputs, but existing approaches either apply global perturbations that may […]
Asymptotic Counting of Binary Phylogenetic Networks
arXiv:2605.23126v1 Announce Type: new Abstract: Phylogenetic networks provide a general framework for modeling reticulate evolutionary processes such as hybridization, recombination, and horizontal gene transfer. In this paper, we study the asymptotic counting of binary phylogenetic networks with $k$ reticulations on $n$ taxa, where $k$ is allowed to grow with $n$. Using edge insertion, we analyze […]
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
arXiv:2605.23384v1 Announce Type: cross Abstract: Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewards (RLVR) derives outcome signals from executable checks or ground-truth answers, but provides limited guidance for intermediate reasoning behaviors. (2) Rubrics-as-reward (RaR) goes beyond final-answer checking by […]
Does Your Wildfire Prediction Model Actually Work, or Just Score Well?
arXiv:2605.18911v2 Announce Type: replace-cross Abstract: Wildfire prediction is important for early warning and resource allocation, yet existing Earth foundation models (Earth FMs) are pretrained for general atmospheric and geophysical objectives rather than wildfire forecasting. To address this gap, we introduce WILDFIRE-FM, the first foundation model pretrained specifically for wildfire prediction using weather, active-fire observations, topography, […]
Abstract relational structures in models of biology
arXiv:2605.23161v1 Announce Type: new Abstract: The mathematical formalisms used to model biological systems induce both latent and ambiguous assumptions that can limit or distort their representational capabilities. Developing formalisms that can represent systems more precisely is fundamental to comprehending their intricacies and complexities. Here we introduce the systems hypergraph, a general and extendable formalism for […]
Goal-Conditioned Agents that Learn Everything All at Once
arXiv:2605.23551v1 Announce Type: cross Abstract: A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is discarded when only performing on-policy updates with respect to the commanded goal. All-goals learning, where each transition is used for learning off-policy with respect to every goal, allows agents […]
Tread lightly interpreting group differences in genetic risk
arXiv:2605.23164v1 Announce Type: new Abstract: Observed differences in mean phenotypic values across human groups have attracted renewed interest with the rise of large-scale genomic studies and polygenic risk prediction. However, the genetic basis of these differences is far more difficult to establish than is often appreciated. Populations can diverge in allele frequency differences without diverging […]
EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation
arXiv:2605.23610v1 Announce Type: cross Abstract: Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory. However, full-frame storage entangles persistent entity information with transient scene context, leading to irrelevant information leakage and high computational cost. We […]
PRAXIS: Case-distilled and code-verified AI agents for biological research
arXiv:2605.23169v1 Announce Type: new Abstract: Large language models are moving scientific research from text assistance toward agentic workflows, yet biological research requires strong object validation, methodological suitability, reproducibility, and auditability. Prompt engineering, general RAG, or tool use alone cannot reliably produce domain-specific scientific judgment. Here, we present PRAXIS, a verifiable biological research agent framework driven […]