Automated discovery systems propose scientific explanations and test which to accept. Does passing a test establish the intended claim? We develop four executable operations for changing physical descriptions: identifying redundancies (L1), coarse-graining dynamics (L2), transferring structure (L3), and inferring missi...
Deep neural networks demonstrate remarkable generalization despite being highly over-parameterized, challenging traditional statistical learning theories. While several theoretical paradigms such as margin-based bounds, PAC-Bayesian analyses, and neural tangent kernels provide global explanations, they often lack mecha...
Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino et al.· 0 citations
How does noisy supervision change the representations learned by a neural network? Training accuracy measures agreement with training labels but provides little information about representation geometry. We use persistent homology to track loop structure across distance thresholds in neural activations. Experiments spa...
Zhongtian Sun, Fan Mo, Prayag Tiwari et al.· 0 citations
In many real-world scenarios we need to consider formal requirements, such as safety and constraint compliance, to deploy Reinforcement Learning (RL) agents. In this paper we introduce RecReg, a safe RL framework capable of enforcing non-Markovian regular safety properties via recovery-based shielding. RecReg is a unif...
Alexander W. Goodall, Francesco Belardinelli· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
LLM-agent memory selection often uses retrieval rankings based on record relevance or individual influence. Such rankings cannot identify sufficient subsets under redundant or jointly necessary evidence. We study per-decision memory sufficiency: selecting a small subset that preserves full-memory behavior. To separate...
Neural combinatorial optimization (NCO) rapidly produces high-quality solutions for problem structures encountered during training, but operational requirements may change after deployment and be communicated in natural language. We propose LangNCO, a framework that compiles instance-specific requirements into structur...
Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved Mixture-of-Experts (MoE) LLMs, but its outcome-level rewards provide only sparse supervision. On-Policy Distillation offers dense token-level feedback, yet requires a stronger compatible teacher, while on-policy self-distillation relies on...
Reinforcement learning with verifiable rewards has become a scalable post-training paradigm for large language models. However, training agents over long-horizon interactions presents two challenges: using only terminal rewards makes turn-level credit assignment sparse and high-variance, while sequential mini-batch upd...
Heming Zou, Qi Wang, Yi-Xiu Mao et al.· 2 citations
Local learning algorithms can reshape resource requirements of artificial intelligence. The memory bottleneck of standard end-to-end backpropagation lies in the need to store all network activations until the loss gradient has been propagated back through. Local learning avoids this, but typically at a cost in accuracy...
Wu-Zi S. Han, Brian A. Yuan, G. Bellec· 0 citations
Graph Convolutional Networks (GCNs) have demonstrated exceptional performance on graph-structured data. However, their success heavily relies on the availability of clean labels, an assumption that often fails in real-world scenarios. The learnability of GCNs is intrinsically linked to the neighborhood structure of nod...
Results identify reward-preserving training structure as a practical route to lower per-step cost in short-window RLVR, and single-problem evaluations provide supporting evidence of retained reasoning quality.
Bang Yang, Hong-Bo Ma, Rui-Han Guo et al.· 0 citations
