arXiv:2611.23244
Goemans's Unsplittable-Flow Conjecture: The Anatomy of AI-Assisted Counterexample DiscoveryThe available reporting indicates from arXiv Machine Learning (cs.LG) that arXiv:2611.23244v1 Announce Type: new Abstract: Goemans conjectured that any fractional single-source flow could be converted into an unsplittable flow without increasing total cost and while increasing any arc load by at most the largest demand
arXiv:2611.23242
Biologically-Inspired Spike Encoding and Optimization for Spiking Neural NetworksThe available reporting indicates from arXiv Machine Learning (cs.LG) that arXiv:2611.23242v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) offer theoretical energy-efficiency advantages over conventional deep networks, but realizing these advantages on vision tasks requires sparse spike representations t
arXiv:2611.23241
GridForge: An Open Physics-Informed Digital Twin and Benchmark Suite for UK 11 kV Underground Distribution CablesThe available reporting indicates from arXiv Machine Learning (cs.LG) that arXiv:2611.23241v1 Announce Type: new Abstract: The UK distribution-cable monitoring sector is data-rich but framework-poor: each Distribution Network Operator (DNO) collects megabytes of telemetry per asset per day, but there is no public bench
arXiv:2611.23240
Neural Network-Based Modeling of Hysteretic Systems: From Prandtl and Preisach Neural Networks to Neuro-Madelung and Neuroplastic Continuous ModelsThe available reporting indicates from arXiv Machine Learning (cs.LG) that arXiv:2611.23240v1 Announce Type: new Abstract: Hysteresis is a complex nonlinear phenomenon characterized by memory dependence, path dependence, and, in many physical systems, degradation, non-congruency, asymmetry, and rate dependence. This re
arXiv:2611.23482
Formal Adequacy Index (based on Polish-language material)The available reporting indicates from arXiv Computation & Language (cs.CL) that arXiv:2611.23482v1 Announce Type: new Abstract: Linguistic formality is one of the dimensions of stylistic variation in speech; however, simply measuring its level does not allow us to determine whether the chosen mode of communication is
arXiv:2611.23403
Tracking Representations in LLM Reasoning Traces for Iterated GamesThe available reporting indicates from arXiv Computation & Language (cs.CL) that arXiv:2611.23403v1 Announce Type: new Abstract: Large language model (LLM) agents achieve state-of-the-art performance across domains through chain-of-thought (CoT) reasoning. Despite their ubiquitous use, little is understood about the re
arXiv:2611.23386
Chorus: Shared N-gram Embeddings with Layer-wise AdaptationThe available reporting indicates from arXiv Computation & Language (cs.CL) that arXiv:2611.23386v1 Announce Type: new Abstract: Language models can gain capacity at little computational cost from n-gram embedding tables: large tables of learned vectors for short sequences of consecutive tokens, which are looked up and
arXiv:2611.23359
Prioritize, Don't Decide: What We Learned Auditing a Deployed Human-in-the-Loop CV SorterThe available reporting indicates from arXiv Computation & Language (cs.CL) that arXiv:2611.23359v1 Announce Type: new Abstract: A single academic vacancy can draw hundreds of applications, and the first screening round consumes most of a committee's time. We describe a CV Priority Sorter deployed at a national platfor
arXiv:2611.23398
HardwareDx: A Foundational Graph Model System for Datacenter Machine RepairsThe available reporting indicates from arXiv Artificial Intelligence (cs.AI) that arXiv:2611.23398v1 Announce Type: new Abstract: The rapid scale-up of AI infrastructure has made datacenter reliability a cornerstone of the cloud business economy. Since hardware failures in hyper-scale AI clusters can stall multi-millio
arXiv:2611.23375
Where the Tokens Go: Heat, Entropy and Error in Agentic CodingThe available reporting indicates from arXiv Artificial Intelligence (cs.AI) that arXiv:2611.23375v1 Announce Type: new Abstract: Coding agents are billed by the token, yet software engineering says nothing about what a token actually buys. Here we introduce a theory of software thermodynamics. The theory draws analogu
arXiv:2611.23365
Training Language Models for Introspective OversightThe available reporting indicates from arXiv Artificial Intelligence (cs.AI) that arXiv:2611.23365v1 Announce Type: new Abstract: Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy. Asking the assistant follow-up questions about
arXiv:2611.23322
Human-AI Mutualism Is Unstable under Capability AsymmetryThe available reporting indicates from arXiv Artificial Intelligence (cs.AI) that arXiv:2611.23322v1 Announce Type: new Abstract: One hope for a good human future alongside advanced AI rests on enduring mutualism: humans and AI will need each other, so the relationship will stay good for both. We argue that this hope f
arXiv:2611.23751
Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent WorkflowThe available reporting indicates from Hugging Face Daily Papers that Autonomous LLM agents incur substantial cost and latency by invoking a large model (System-2) at every step, even when many intermediate actions choose among a small set of known candidates. Existing dual-system agents offload such decisions to a lig
arXiv:2611.23499
BiCAT: Bimanual Coordination Action TokenizationThe available reporting indicates from Hugging Face Daily Papers that Autoregressive vision-language-action (VLA) models predict discrete action tokens with the next-token objective of their vision-language backbone, so the action tokenizer defines the interface between the policy and the robot. In bimanual manipulatio
arXiv:2611.17600
LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular LearningThe available reporting indicates from Hugging Face Daily Papers that Multimodal tabular learning involves classification and regression on tables combining structured numerical and categorical features with unstructured text and images. These unstructured fields are commonly represented by pretrained encoder embedding
paper-0ab1e7b9aa
Multimodal cell foundation models require synergistic integration beyond alignmentThe available reporting indicates from Nature Machine Intelligence that Nature Machine Intelligence, Published online: 09 November 2026; doi:10.1038/s42256-026-01328-3 Richter et al. show that simply aligning different types of biological data does not fully integrate them, revealing when data repeat the same informati