Knowledge catalogue
arXiv:2610.18579v1 Announce Type: new Abstract: System One models choose an agent's next action by scoring a supplied set of options in a single pass. This makes them fast and cheap, but when they cho
arXiv:2610.20503v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by drafting multiple tokens per step, yet feature-based drafters rely on target hidden featur
arXiv:2610.20369v1 Announce Type: new Abstract: Neural partial differential equation (PDE) surrogates trained with mean squared error (MSE) can capture dominant dynamics but often lose high-frequency
arXiv:2610.17271v1 Announce Type: new Abstract: Propaganda detection systems usually operate as black boxes, lacking explanations. To address this, we hypothesise that persuasive techniques contain de
arXiv:2610.15642v1 Announce Type: new Abstract: Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively suff
arXiv:2610.15259v1 Announce Type: new Abstract: Low-bit quantization reduces the cost of serving reasoning models but can substantially degrade long chains of thought. Each step reads cached keys and
arXiv:2610.19082v1 Announce Type: new Abstract: Robotic systems that must acquire information about a specific target often face severe occlusion from sur- rounding structures or from the target itsel
arXiv:2510.23160v2 Announce Type: replace Abstract: Data selection for supervised fine-tuning (SFT) often discards low-scoring instruction examples that may retain useful supervision. We propose a rul
arXiv:2610.19723v1 Announce Type: new Abstract: Interpreting an ambiguous utterance in real-world interactions often requires context beyond a single utterance. When the utterance refers to objects in
arXiv:2610.20572v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student model on its own rollouts with token-level supervision from a teacher, assuming that the teacher can reach
arXiv:2601.11100v3 Announce Type: replace Abstract: Large Language Model (LLM) agents are reshaping the industrial landscape. However, most practical agents still rely on human-designed scaffolds, mak
arXiv:2610.16397v1 Announce Type: new Abstract: We study environment scaling as a way to increase agent-benchmark difficulty while holding core task objectives fixed. Our framework, Recursive Environm
arXiv:2610.04561v2 Announce Type: replace Abstract: Differentiable programming connects scientific computation with gradient-based inference, learning and design. Extending these capabilities across a
arXiv:2610.19530v1 Announce Type: new Abstract: As a lightweight and highly accurate method for nearest-neighbor search in 3D point clouds, approaches based on space-filling curves (SFC) have been pro
arXiv:2610.14495v1 Announce Type: new Abstract: Explainer videos -- a worked geometry problem, why the sky is blue, how a dynasty fell -- are usually one more target for pixel video generation. We arg
arXiv:2610.20352v1 Announce Type: new Abstract: Multimodal Large Language Models have made significant progress in referring expression comprehension (REC), yet most REC benchmarks still focus on fina
arXiv:2610.19765v1 Announce Type: new Abstract: Computationally lightweight manipulation policies predict executable actions with low inference latency, but prediction errors can limit task success. I
arXiv:2610.19246v1 Announce Type: new Abstract: Equivariant structure-prediction pipelines alternate coordinate updates with the construction of a k-nearest-neighbour (kNN) graph whose membership is a
arXiv:2610.19700v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) enables parameter-efficient fine-tuning by learning low-rank weight updates. Increasing rank expands adaptation capacity, but
arXiv:2610.19783v1 Announce Type: new Abstract: Reinforcement learning (RL) holds the promise of learning a policy that can outperform what is shown in the data. However, in practice, such systems suf
arXiv:2610.14721v1 Announce Type: new Abstract: Test-Time Discovery (TTD) aims to recognize known classes and detect novel ones from a continuous unlabeled test stream after deployment. Existing TTD m
arXiv:2610.17205v1 Announce Type: new Abstract: LLM-based decision-making systems, also called System One models, have recently gained popularity, most notably through Jev (Almeida, 2026). Given a typ
Relevant to the comprehension challenge I posed in 2014 and my bet with Miles Brundage. We edited Mark Twain's Huckleberry Finn and fed it to 9 AI models to summarize a chapter, twice each. Only Claud
arXiv:2610.20543v1 Announce Type: new Abstract: Multimodal sentiment models are usually evaluated on complete utterances, yet streams often lose a contiguous span of text, audio, or video. We study lo
arXiv:2610.17305v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently improved Text-to-SQL generation, but their computational cost can hinder deployment in resource-constrained s
arXiv:2610.19674v1 Announce Type: new Abstract: Geometry foundation models estimate camera poses and 3D scene structure from video sequences, but maintaining consistent reconstructions over long horiz
arXiv:2610.19832v1 Announce Type: new Abstract: Reward model overoptimization in RLHF is usually described as reward hacking. We recast it as rent-seeking: the policy, a firm, earns reward from a regu
arXiv:2610.20253v1 Announce Type: new Abstract: Speech-capable language models inherit most of their knowledge from text-rich language backbones, and continued model maintenance is likewise dominated
arXiv:2610.20111v1 Announce Type: new Abstract: Distilling pretrained video diffusion models into few-step autoregressive (AR) generators typically combines student initialization with distribution ma
arXiv:2610.20608v1 Announce Type: new Abstract: Representation-alignment methods effectively accelerate the diffusion transformer training. REPA, for example, uses a pretrained vision encoder to super
arXiv:2601.09041v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often produce judgments similar to those of humans, but their interpretation of figurative language remains uncle
arXiv:2610.15513v1 Announce Type: cross Abstract: Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming
arXiv:2610.19810v1 Announce Type: cross Abstract: Large language models are increasingly competent at leveraging scientific knowledge and existing computational tools to execute complex workflows. At
arXiv:2610.18204v1 Announce Type: cross Abstract: Connection-tableau provers typically construct closed tableaux by backtracking search. This gives lightweight proof procedures, but their low-memory s
arXiv:2610.20274v1 Announce Type: cross Abstract: Learnable downsampling and spectral-domain filter parameterizations have each made convolutional networks more flexible, but their interaction has not
arXiv:2610.16315v1 Announce Type: new Abstract: Test-time agentic computation can improve multimodal large language models (MLLMs) through planning, tool use, iterative perception, and reflection, but
arXiv:2608.28399v2 Announce Type: replace Abstract: In financial markets, a sequential policy that reacts systematically to price movements may become predictable to other market participants. This pa
arXiv:2601.17226v3 Announce Type: replace-cross Abstract: Counterfactual storytelling exposes LLM shortcomings in causal reasoning, where few-shot prompting and SFT fail to produce logical and rationa
arXiv:2610.20071v1 Announce Type: new Abstract: MeanFlow predicts interval-average velocities, but conventional few-step sampling ties the interval queried from the model to the duration of the state
arXiv:2610.18566v1 Announce Type: new Abstract: Large language model (LLM) routers reduce serving cost by choosing which model to call and how many output tokens to grant it for each query. Existing r
arXiv:2610.03948v3 Announce Type: replace Abstract: Autonomous driving decision systems must balance safety, efficiency, and social norms in complex traffic interactions. Philosophical and ethical con
arXiv:2610.20243v1 Announce Type: new Abstract: Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Desp
arXiv:2610.19528v1 Announce Type: new Abstract: Retrieving external knowledge can improve large language model (LLM) translation by providing supplementary information such as idiom interpretations an
arXiv:2610.15884v1 Announce Type: new Abstract: False retry permission (FRP) occurs when an agent retries a timed-out tool call without support from the visible contract. RetryBench separates this err
arXiv:2610.16288v2 Announce Type: new Abstract: Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents. D
arXiv:2610.15897v2 Announce Type: cross Abstract: Qwen3-8B reviewing Llama-3.1-8B in math adds 33.2 points, yet Qwen3-8B alone is 6.4 points more accurate than the result. Reviewing another model's an
arXiv:2610.19065v1 Announce Type: cross Abstract: Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers h
arXiv:2610.20534v1 Announce Type: new Abstract: Relational deep learning has emerged as a powerful paradigm for learning end-to-end predictive models over relational databases by representing them as
arXiv:2610.15991v1 Announce Type: new Abstract: Distributed agent workflows cache delegated authority at tool gateways. Revocation may be reported at issuer commit, transport acknowledgment, or receiv
arXiv:2610.19561v1 Announce Type: new Abstract: An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to
arXiv:2610.19220v1 Announce Type: cross Abstract: The Continuous Thought Machine (CTM) is a recurrent network that attends to inputs and makes predictions based on the synchronization between its neur
arXiv:2609.32817v2 Announce Type: replace Abstract: Clinical Large Language Models (LLMs) achieve strong medical-exam accuracy; however, a correct answer does not guarantee that the explanation names
arXiv:2610.19044v1 Announce Type: cross Abstract: Tiny robots have limited computation and memory, yet visual navigation systems often maintain more state than a task requires. We ask whether persiste
arXiv:2610.15919v1 Announce Type: cross Abstract: Supervised machine learning in high-energy physics (HEP) requires training on labeled simulations of particle collisions, which are known to be unfait
arXiv:2610.19630v1 Announce Type: cross Abstract: Automated materials discovery requires evaluating large pools of candidate configurations, with density functional theory (DFT) as a major throughput
arXiv:2602.03100v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as agents that operate in real-world environments, introducing safety risks beyond linguistic
arXiv:2610.17266v1 Announce Type: new Abstract: Diffusion language models are a promising and more efficient alternative to autoregressive models. However, most RL post-training techniques are not eas
arXiv:2610.20174v1 Announce Type: cross Abstract: Reinforcement Learning on Mixed-domain preference data (Mix-RL) has become the mainstream approach for training general-purpose Generative Reward Mode
arXiv:2610.03966v2 Announce Type: replace Abstract: Each run of an AI-driven research system (ADRS) is an expensive search over a vast solution space, and dependable evaluation requires many runs, mak
arXiv:2610.19594v1 Announce Type: new Abstract: Whole-body mobile manipulation suffers from two fundamental challenges: inherent motion heterogeneity across locomotion, arm, and hand modules, and prog