All entries

arXiv:2610.20203v1 Announce Type: cross Abstract: This paper investigates the use of Behavior Cloning (BC) for autonomous driving from a bird's-eye view (BEV) perspective in simulated urban environmen

arXiv:2610.19016v1 Announce Type: new Abstract: Regret matching (and its variants) and counterfactual regret minimization are central algorithms in practice for normal-form and extensive-form game sol

arXiv:2602.08318v3 Announce Type: replace-cross Abstract: Flow matching (FM) is increasingly used in scientific domains for time series generation and forecasting, where data often arise from underlyi

arXiv:2610.14073v1 Announce Type: cross Abstract: Large language models (LLMs) remain unreliable when reasoning about the future. Existing models often overlook the difference among future states, com

arXiv:2610.14576v1 Announce Type: new Abstract: As frontier LLMs gain more capabilities, the cost to run them also goes up. At the same time, small language models (SLMs) also gain more capabilities b

arXiv:2510.24469v2 Announce Type: replace-cross Abstract: Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical

arXiv:2610.19638v1 Announce Type: new Abstract: We present J-tau, the first publicly available Japanese benchmark for evaluating tool-using LLM agents in interactive customer-support scenarios. While

arXiv:2603.26515v2 Announce Type: replace-cross Abstract: Efficient and robust turn-taking detection remains a significant challenge in industrial-grade voice AI agents. Existing systems often rely on

arXiv:2610.19792v1 Announce Type: new Abstract: Speculative decoding's effectiveness is governed by two quantities: the acceptance rate of drafted tokens and the cost of producing them. We show the tw

arXiv:2610.18610v1 Announce Type: cross Abstract: Dialogue and collaborative assistants repeatedly judge what a partner knows, believes, or intends. Typed decision models offer a potential alternative

arXiv:2610.18773v1 Announce Type: new Abstract: System one models enable direct, low-latency decision-making. Yet recent practice of predicting an answer from serialized text does not, by itself, resp

arXiv:2610.18272v1 Announce Type: cross Abstract: Autonomous research agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leavi

arXiv:2610.14699v1 Announce Type: new Abstract: The design of high-affinity, target-specific protein binders is central to the development of modern therapeutics. However, existing protein-generation

arXiv:2610.19026v1 Announce Type: new Abstract: Sparse attention reduces the KV-cache traffic that dominates long-context LLM decoding, but practical methods largely operate at coarse granularity. Tok

arXiv:2610.19822v1 Announce Type: cross Abstract: LLM agents are evolving from a single model calling tools to planners that orchestrate multiple expert models whose capabilities live in distinct weig

arXiv:2610.18497v1 Announce Type: new Abstract: Tool-call judges evaluate argument values proposed by LLM agents. We find that they accept a correct value less often when their input holds no referenc

arXiv:2610.19290v1 Announce Type: new Abstract: We present Kandinsky S2V 1.0, an open family of speech-to-video models for controllable audio-driven human animation, comprising Kandinsky S2V 1.0 Lite

arXiv:2610.20117v1 Announce Type: new Abstract: KANLab is a browser-based visualization tool designed to interactively teach the core concepts of Kolmogorov-Arnold Networks (KAN), forked from the wide

arXiv:2610.17719v1 Announce Type: new Abstract: Agents build knowledge graphs as memory, and building them has become easy. Maintaining them has not. When a source is retracted, overruled, or erased,

arXiv:2610.20552v1 Announce Type: new Abstract: We present KinoGen, a framework that synthesizes customizable humanoid loco-manipulation references through kinematically grounded video generation. Kin

arXiv:2604.03414v2 Announce Type: replace Abstract: Video Large Language Models (Video LLMs) achieve strong performance on video understanding tasks but suffer from high inference costs due to the lar

arXiv:2610.18616v1 Announce Type: cross Abstract: Searching text-rich knowledge graphs requires following relations while examining textual evidence. Predefined graph interfaces constrain what evidenc

arXiv:2610.15677v1 Announce Type: new Abstract: Continual learning aims to adapt pretrained large language models (LLMs) to evolving data while preserving their pretrained capabilities. A central chal

arXiv:2610.15081v1 Announce Type: new Abstract: Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic capacity underlying gene

arXiv:2610.19399v1 Announce Type: new Abstract: Korean neologisms arise through diverse mechanisms, a demanding test of language models beyond lexical memorization. To enable systematic evaluation, we

arXiv:2610.19591v1 Announce Type: cross Abstract: The lasting gains in AI have come from methods that absorb more computation, and language models already scale computation within a call. Useful work,

arXiv:2610.16182v1 Announce Type: new Abstract: Flagship large language models (LLMs) offer rich general knowledge and strong reasoning capabilities, but their high inference cost and latency limit th

arXiv:2608.01718v2 Announce Type: replace Abstract: Semantic caching, reusing responses to answer semantically similar queries, has seen growing adoption in LLM serving, offering faster responses and

arXiv:2610.19038v1 Announce Type: new Abstract: We study online task assignment with reusable resources. This problem arises in peer reviewer assignment, skill-based call routing, rideshare matching,

arXiv:2610.18950v1 Announce Type: cross Abstract: Humanoid loco-manipulation requires coordinated whole-body interaction with the physical world, yet collecting robot demonstrations at scale remains c

arXiv:2610.19266v1 Announce Type: new Abstract: Existing illumination estimation methods primarily recover lighting distributions for rendering, but typically leave the contributions of individual phy

arXiv:2610.20102v1 Announce Type: new Abstract: We investigate two aspects of multilingual pre-training with limited data, namely how language exposure is distributed across English, Dutch, and Chines

arXiv:2602.02326v3 Announce Type: replace Abstract: If multilingual language model representations contain separable language-associated structure, then shifting between languages may require only sim

arXiv:2610.15501v1 Announce Type: new Abstract: Large language models make decisions through parallel prefill and sequential decoding. Although effective, this approach incurs decoding costs and does

arXiv:2610.16140v1 Announce Type: new Abstract: Transportation planning has traditionally required substantial expertise in network modeling, traffic assignment, and optimization. As a result, strateg

arXiv:2610.15994v1 Announce Type: new Abstract: Representing individual-level behavioral heterogeneity is challenging in epidemiological modeling, particularly when empirical behavioral data are spars

arXiv:2610.17439v1 Announce Type: new Abstract: The success of autonomous research systems relies on the quality of the scientific hypotheses they generate. Recent studies report that human reviewers

arXiv:2610.19444v1 Announce Type: cross Abstract: Random reshuffling stochastic gradient descent (RR-SGD) is widely used for finite-sum optimization in machine learning. For convex L-smooth components

arXiv:2610.14552v1 Announce Type: cross Abstract: Protocol specifications rarely justify executable behavior in one place: a transition may inherit its source state from a remote control block, name i

arXiv:2610.14766v1 Announce Type: cross Abstract: AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear. We introduce the Last Secure Code Benchmark,

arXiv:2610.16625v1 Announce Type: new Abstract: Post-route FPGA timing closure remains expert-dependent and computationally expensive. We present LATCH (LLM-Assisted Timing Closure Harness), a two-lay

arXiv:2603.23784v1 Announce Type: cross Abstract: Grokking-the phenomenon where validation accuracy of neural networks on modular addition of two integers rises long after training data has been memor

arXiv:2610.20582v1 Announce Type: new Abstract: Long contexts enlarge key--value (KV) caches, increasing memory use and attention costs during generation. Compressing these caches must preserve inform

arXiv:2610.19975v1 Announce Type: new Abstract: Looped Mixture-of-Experts (MoE) models combine parameter reuse with sparse computation to improve performance under matched budgets. Prior work demonstr

arXiv:2610.18014v1 Announce Type: cross Abstract: Non-prefix KV cache reuse is a promising approach for improving inference efficiency in multi-agent systems as agents share the same context blocks. H

arXiv:2610.20585v1 Announce Type: cross Abstract: Current approaches for steady partial differential equations surrogate models on unstructured meshes apply a single mixing mechanism to the whole solu