Knowledge catalogue
quick, name a prominent company that achieved a major win via tokenmaxxing! I've yet to see, or hear of a company that is winning against its competition, because said company is spending more on AI t
arXiv:2605.29500v1 Announce Type: cross Abstract: Off-policy evaluation estimates how a target policy would perform using data collected by a different behavior policy, which is crucial when online te
arXiv:2605.30280v1 Announce Type: cross Abstract: Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented cap
arXiv:2605.29538v1 Announce Type: new Abstract: With the emergence of wireless applications in three-dimensional environments, such as the low-altitude airspace and 3D heterogeneous networks, radio ma
arXiv:2605.30029v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context
arXiv:2602.06791v2 Announce Type: replace Abstract: Being probabilistic models, during inference large language models (LLMs) display rare events: behaviour that is far from typical but highly signifi
Ray Data LLM, developed by Anyscale, achieves 2x higher throughput compared to vLLM's synchronous LLM engine when operating at production scale. This performance improvement likely stems from Ray Data
arXiv:2605.29579v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have achieved rapid progress in vision-language understanding, they remain prone to multimodal hallucinat
arXiv:2605.29151v1 Announce Type: cross Abstract: We prove real-rootedness for the Poincare polynomial [ P_n(t)=sum_{i=0}^{n-3} im H^{2i}(overline{mathcal M}_{0,n};Q)t^i ] of the Deligne--Mumford modu
arXiv:2605.29412v1 Announce Type: cross Abstract: This paper presents the real-time retargeting guidance policy developed for the Chandrayaan-3 lunar landing mission. The baseline guidance generates a
arXiv:2605.29729v1 Announce Type: new Abstract: We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming
arXiv:2605.29114v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between
arXiv:2602.02909v2 Announce Type: replace Abstract: Inference-time scaling via chain-of-thought (CoT) reasoning is a major driver of state-of-the-art LLM performance, but it comes with substantial lat
arXiv:2602.00994v2 Announce Type: replace Abstract: Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most
arXiv:2605.29327v1 Announce Type: new Abstract: Efficient Distillation (EDistill) compresses large language models (LLMs) by structured pruning parameters and tuning lightweight modules with high trai
arXiv:2605.28913v1 Announce Type: new Abstract: Large reasoning models (LRMs) often generate extensive chain-of-thought (CoT) traces before producing a final answer. As explicit textual artifacts, the
arXiv:2603.05488v4 Announce Type: replace-cross Abstract: We provide evidence of performative chain-of-thought (CoT) in reasoning models, where a model becomes strongly confident in its final answer,
arXiv:2601.22139v2 Announce Type: replace-cross Abstract: Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain funda
arXiv:2605.30327v1 Announce Type: cross Abstract: Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing th
arXiv:2605.29425v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promise in traffic signal control (TSC). However, its reliance on predefined states limits responsiveness to obser
arXiv:2605.29192v1 Announce Type: new Abstract: Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack a vocabulary for describing their internal structu
Reconstructing software engineering around AI is going to take work (even as the ability of AI to code increases at a rapid rate). Organizations are ideally spending tokens for two things: 1) building
arXiv:2605.30021v1 Announce Type: new Abstract: Many open-ended instructions have multiple valid answers that users can benefit from seeing, but post-training often narrows an LLM's output space towar
arXiv:2605.29447v1 Announce Type: cross Abstract: While GUI agents have advanced rapidly, they often lack the robustness to recover from their own errors, hindering real-world deployment. To bridge th
arXiv:2602.01456v2 Announce Type: replace-cross Abstract: Joint-Embedding Predictive Architectures (JEPA) learn view-invariant representations and admit projection-based distribution matching for coll
arXiv:2602.20141v2 Announce Type: replace Abstract: Mean Field Games (MFGs) provide a principled framework for modelling interactions in large population systems. However, algorithmic progress has bee
arXiv:2605.29911v1 Announce Type: cross Abstract: We propose a machine learning approach for image regression from sparse experimental measurements. We show the application of the proposed method on f
arXiv:2605.29893v1 Announce Type: new Abstract: LLM-based agents have demonstrated strong capabilities in solving complex tasks through multi-step reasoning and tool use. However, existing evaluation
arXiv:2605.30244v1 Announce Type: cross Abstract: While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partial
arXiv:2605.26108v2 Announce Type: replace Abstract: Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains
arXiv:2603.07916v2 Announce Type: replace Abstract: In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to str
arXiv:2605.29634v1 Announce Type: new Abstract: Transformer hidden states are often interpreted through local or low-order objects: neurons, sparse features, attention heads, residual-stream direction
arXiv:2605.29224v1 Announce Type: cross Abstract: AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating
Reliability shouldn't require reserving GPUs. Serverless 2.0 is live on Fireworks: one API, 3 serving paths. → Standard: elastic default → Priority: sheds last under congestion, pricing ~1.5x standard
arXiv:2605.29687v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at understanding natural language but struggle with optimisation tasks involving multiple constraints and user-define
arXiv:2605.29973v1 Announce Type: new Abstract: Robot behavior is often validated through simulation-based testing, yet the replicability of such campaigns depends critically on transparent documentat
arXiv:2605.30052v1 Announce Type: cross Abstract: One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the traject
arXiv:2605.28870v1 Announce Type: cross Abstract: We investigate the Platonic Representation Hypothesis (PRH) through a tripartite statistical framework of representations: signal, bias, and noise. {1
arXiv:2605.28850v1 Announce Type: new Abstract: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. Using TradeArena, an
arXiv:2601.21564v2 Announce Type: replace Abstract: Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concern
arXiv:2510.00936v2 Announce Type: replace Abstract: Cross-resolution person re-identification (CR-ReID) remains challenging in practical surveillance, where camera quality and capture distance lead to
arXiv:2605.30315v1 Announce Type: new Abstract: Across two public LLM leaderboards, many displayed pairwise rankings do not meet a conventional paired-test resolution target under the actual paired ev
arXiv:2605.28962v1 Announce Type: new Abstract: Diffusion bridge models offer a powerful framework for connecting two data distributions, such as in image restoration and translation. Many existing me
arXiv:2605.30338v1 Announce Type: new Abstract: Reconstructing physically stable 3D scenes from a single RGB image enables casual images to be converted into simulation-ready digital assets for applic
arXiv:2605.29335v1 Announce Type: cross Abstract: Frechet Inception Distance (FID) is widely used to evaluate image generators, yet lower FID does not always correspond to better sample quality. We sh
arXiv:2605.29234v1 Announce Type: new Abstract: We study large-scale literature search from two complementary angles: improving the retrieval pipeline, and stress-testing the human reference list as a
arXiv:2605.29401v1 Announce Type: new Abstract: Time-Series Foundation Models (TSFMs) excel at zero-shot unimodal forecasting using numerical data, but unlike LLMs they cannot consume multimodal, non-
arXiv:2605.29319v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on table reasoning tasks but incur substantial inference cost due to long reasoning traces. Ste
arXiv:2605.29028v1 Announce Type: cross Abstract: Conditioned Sequence Models (CSMs) learn policies by treating return-to-go (RTG) as a control signal. However, existing CSMs often treat the RTGs as s
arXiv:2605.28897v1 Announce Type: new Abstract: LLM-generated reviews for scientific papers are gaining considerable traction and are even being officially piloted by major conferences. We have to ass
arXiv:2605.29397v1 Announce Type: new Abstract: HTML observations in LLM-based web agents are extremely long, and while many reduction methods have been proposed, it remains unclear which methods redu
arXiv:2603.18859v2 Announce Type: replace Abstract: Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process
arXiv:2603.27758v2 Announce Type: replace Abstract: Metric Cross-View Geo-Localization (MCVGL) aims to estimate the 3-DoF camera pose (position and heading) by matching ground and satellite images. In
arXiv:2605.30059v1 Announce Type: new Abstract: We connect stochastic resetting from non-equilibrium statistical physics with ridge regularization in statistical learning. For linear gradient flow, re
arXiv:2601.18728v2 Announce Type: replace Abstract: Modern generative modeling methods have demonstrated strong performance in learning complex data distributions from clean samples. In many scientifi
arXiv:2605.28827v1 Announce Type: new Abstract: Open Arabic large language models split into two classes: sub-1B multilingual models that treat Arabic as an afterthought (Qwen2.5-0.5B, Falcon-H1-0.5B)
arXiv:2509.05771v2 Announce Type: replace-cross Abstract: We develop a new classification framework based on the theory of coherent risk measures and systemic risk. The proposed approach is suitable f
arXiv:2605.30154v1 Announce Type: new Abstract: Correctness-based Reinforcement Learning with Verifiable Rewards (RLVR) trains language models from binary feedback on sampled outputs, but the objectiv
arXiv:2605.30326v1 Announce Type: cross Abstract: The ability to reason, adapt, and creatively solve problems under unexpected challenges is essential for robots operating in real-world environments.
arXiv:2605.29068v1 Announce Type: new Abstract: Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrai