arXiv:2605.04752v1 Announce Type: cross Abstract: Accurate traffic congestion classification requires models that jointly capture roadway scene context and non-stationary traffic motion, yet most prior work treats these requirements in isolation. Vision-based methods often depend on appearance cues with standard temporal pooling, which can bias predictions toward static infrastructure, whereas signal-based approaches characterize temporal dynamics but […]
Parallel Prefix Verification for Speculative Generation
arXiv:2605.04263v1 Announce Type: new Abstract: We introduce PARSE (PArallel pRefix Speculative Engine), a speculative generation framework that accelerates large language model (LLM) inference by parallelizing prefix verification on a semantic level. Existing speculative decoding methods are fundamentally limited by token-level equivalence: the target model must verify each token, leading to short acceptance lengths and modest […]
LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy
arXiv:2605.04295v1 Announce Type: cross Abstract: LLMs’ overconfidence, particularly when hallucinating, poses a significant challenge for the deployment of the models in safety-critical settings and makes a reliable estimation of uncertainty necessary. Existing approaches for uncertainty quantification typically prioritize lexical or probabilistic measures; however, these techniques often ignore the semantic variance of different responses with similar […]
Grokability in five inequalities
arXiv:2605.05193v1 Announce Type: cross Abstract: In this note, we report five mathematical discoveries made in collaboration with Grok, all of which have been subsequently verified by the authors. These include an improved lower bound on the maximal Gaussian perimeter of convex sets in $mathbbR^n$, sharper $L_2$-$L_1$ moment comparison inequalities on the Hamming cube $-1,1^n$, a […]
Resilient AI Supercomputer Networking using MRC and SRv6
arXiv:2605.04333v1 Announce Type: cross Abstract: Tail latency dominates the performance of synchronous pretraining jobs when running at very large scales. We describe a three-pronged approach: (1) a new RDMA-based transport protocol, MRC, sprays across many paths and actively load-balances between them, eliminating the issue of flow collisions (2) the use of multi-plane Clos topologies to […]
Benchmarking open-source tools for in silico antiviral drug discovery
arXiv:2605.04265v1 Announce Type: new Abstract: Antivirals are uniquely positioned to be deployed quickly during a new outbreak, especially when repurposed from approved drugs. Yet there are no FDA-approved antivirals for the majority of viral families with pandemic potential. Here we lay out the case for investing in technologies and techniques for antiviral drug discovery and […]
Classification of SARS-CoV-2 Variants through The Epistatical Circos Plots with Convolutional Neural Networks
arXiv:2601.22866v2 Announce Type: replace Abstract: The COVID-19 pandemic has profoundly affected global health, driven by the remarkable transmissibility and mutational adaptability of the SARS-CoV-2 virus. Although five variants of concern, Alpha, Beta, Gamma, Delta, and Omicron, have been identified, the classification task in this study is formulated using four classes: Alpha, Delta, Omicron, and Else, […]
Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery
arXiv:2605.04375v1 Announce Type: cross Abstract: To unleash the full potential of AI for Science, we must untether the agents from a purely digital environment. The agent’s ability to control and explore in real-world labs is essential because the physical lab remains foundational to scientific discovery. While some tasks can be performed on a computer (e.g., […]
Agent Island: A Saturation- and Contamination-Resistant Benchmark from Multiagent Games
arXiv:2605.04312v1 Announce Type: new Abstract: Static capabilities benchmarks suffer from saturation and contamination, making it difficult to track capabilities progress over time. We introduce Agent Island, a multiplayer simulation environment in which language-model agents compete in a game of interagent cooperation, conflict, and persuasion. The environment yields a dynamic benchmark designed to mitigate both saturation […]
Demystifying Manifold Constraints in LLM Pre-training
arXiv:2605.04418v1 Announce Type: cross Abstract: The empirical success of large language model (LLM) pre-training relies heavily on heuristic stabilization techniques, such as explicit normalization layers and weight decay. While recent constrained optimization approaches that explicitly restrict weights may improve numerical stability and performance, the mechanism and motivation for adding constraints still remain elusive. This paper […]
The Effects of Visual Priming on Cooperative Behavior in Vision-Language Models
arXiv:2604.27953v2 Announce Type: replace Abstract: As Vision-Language Models (VLMs) become increasingly integrated into decision-making systems, it is essential to understand how visual inputs influence their behavior. This paper investigates the effects of visual priming on VLMs’ cooperative behavior using the Iterated Prisoner’s Dilemma (IPD) as a test scenario. We examine whether exposure to images depicting […]
GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
arXiv:2605.04449v1 Announce Type: cross Abstract: Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models (LLMs) struggle despite their impressive general capabilities. We present GEM (Graph-Enhanced Mixture-of-Experts), a novel framework that combines language models and graph-structured dialogue understanding with ReAct agent-based reasoning for superior DST performance. […]