arXiv:2604.03361v1 Announce Type: cross Abstract: The modeling of bio-molecular system across molecular scales remains a central challenge in scientific research. Large language models (LLMs) are increasingly applied to bio-molecular discovery, yet systematic evaluation across multi-scale biological problems and rigorous assessment of their tool-augmented capabilities remain limited. We reveal a systematic gap between LLM performance and […]
When Adaptive Rewards Hurt: Causal Probing and the Switching-Stability Dilemma in LLM-Guided LEO Satellite Scheduling
arXiv:2604.03562v1 Announce Type: new Abstract: Adaptive reward design for deep reinforcement learning (DRL) in multi-beam LEO satellite scheduling is motivated by the intuition that regime-aware reward weights should outperform static ones. We systematically test this intuition and uncover a switching-stability dilemma: near-constant reward weights (342.1 Mbps) outperform carefully-tuned dynamic weights (103.3+/-96.8 Mbps) because PPO requires […]
Generative AI for material design: A mechanics perspective from burgers to matter
arXiv:2604.03409v1 Announce Type: cross Abstract: Generative artificial intelligence offers a new paradigm to design matter in high-dimensional spaces. However, its underlying mechanisms remain difficult to interpret and limit adoption in computational mechanics. This gap is striking because its core tools-diffusion, stochastic differential equations, and inverse problems-are fundamental to the mechanics of materials. Here we show […]
Regime Mapping of Oscillatory States in Balanced Spiking Networks with Multiple Time Scales
arXiv:2604.04770v1 Announce Type: cross Abstract: Balanced spiking networks can transition between silent, asynchronous-irregular, and oscillatory states depending on interacting synaptic and temporal time scales, while their joint parameter structure remains incompletely characterized. In this work, we systematically map how postsynaptic decay (taus), conduction delay (d), and plasticity rate (lambdap) jointly shape oscillatory regimes in recurrent […]
MetaSAEs: Joint Training with a Decomposability Penalty Produces More Atomic Sparse Autoencoder Latents
arXiv:2604.03436v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single coherent concept drawn from a single underlying representational subspace. In practice, SAE latents blend representational subspaces together. […]
Personality Requires Struggle: Three Regimes of the Baldwin Effect in Neuroevolved Chess Agents
arXiv:2604.03565v1 Announce Type: new Abstract: Can lifetime learning expand behavioral diversity over evolutionary time, rather than collapsing it? Prior theory predicts that plasticity reduces variance by buffering organisms against environmental noise. We test this in a competitive domain: chess agents with eight NEAT-evolved neural modules, Hebbian within-game plasticity, and a desirability-domain signal chain with imagination. […]
RDFace: A Benchmark Dataset for Rare Disease Facial Image Analysis under Extreme Data Scarcity and Phenotype-Aware Synthetic Generation
arXiv:2604.03454v1 Announce Type: cross Abstract: Rare diseases often manifest with distinctive facial phenotypes in children, offering valuable diagnostic cues for clinicians and AI-assisted screening systems. However, progress in this field is severely limited by the scarcity of curated, ethically sourced facial data and the high similarity among phenotypes across different conditions. To address these challenges, […]
Analyzing Symbolic Properties for DRL Agents in Systems and Networking
arXiv:2604.04914v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) has shown remarkable performance on complex control problems in systems and networking, including adaptive video streaming, wireless resource management, and congestion control. For safe deployment, however, it is critical to reason about how agents behave across the range of system states they encounter in practice. Existing […]
Selective Forgetting for Large Reasoning Models
arXiv:2604.03571v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) generate structured chains of thought (CoTs) before producing final answers, making them especially vulnerable to knowledge leakage through intermediate reasoning steps. Yet, the memorization of sensitive information in the training data such as copyrighted and private content has led to ethical and legal concerns. To address […]
Optimizing Neurorobot Policy under Limited Demonstration Data through Preference Regret
arXiv:2604.03523v1 Announce Type: cross Abstract: Robot reinforcement learning from demonstrations (RLfD) assumes that expert data is abundant; this is usually unrealistic in the real world given data scarcity as well as high collection cost. Furthermore, imitation learning algorithms assume that the data is independently and identically distributed, which ultimately results in poorer performance as gradual […]
Similarity Field Theory: A Mathematical Framework for Intelligence
arXiv:2509.18218v5 Announce Type: replace Abstract: We posit that transforming similarity relations form the structural basis of comprehensible dynamic systems. This paper introduces Similarity Field Theory, a mathematical framework that formalizes the principles governing similarity values among entities and their evolution. We define: (1) a similarity field $S: U times U to [0,1]$ over a universe […]
Thermal fluctuations set fundamental limits on ion channel function
arXiv:2604.03538v1 Announce Type: cross Abstract: Voltage-gated ion channels are essential for propagating signals in neurons. Each channel senses the local membrane potential created by nearby ions. Fluctuations in these ions introduce two fundamental noise sources: (i) shot noise, from the discreteness of ionic charge, and (ii) Johnson-Nyquist noise, from long-wavelength thermal fluctuations of the electric […]