Knowledge catalogue
arXiv:2605.30833v1 Announce Type: cross Abstract: On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from
Nous Research announced significant developments or milestones for Hermes Agent, their AI agent framework, indicating multiple new capabilities, updates, or releases during that particular week. The a
Learn more about the latest from @james_y_zou and our Frontier Agents Research team! To evaluate frontier AI agents, we need more complex tasks. But such tasks are also more prone to have design mista
The efficiency frontier! Where do you think GPT-5.6 will land? Claude Opus 4.8 has landed on DeepSWE Bench, posting a 58% Pass@1 and taking #2 overall behind GPT-5.5. It continues a broader trend: sli
arXiv:2605.29410v1 Announce Type: new Abstract: Reliable midair docking between small unmanned aerial vehicles (UAVs) is essential for modular aerial cooperation and manipulation, but it requires prec
arXiv:2605.29698v1 Announce Type: new Abstract: Machine learning for molecular property prediction has focused largely on pure compounds, even though many practical applications depend on mixtures wit
arXiv:2605.29926v1 Announce Type: new Abstract: Accurate prediction of drug-target interactions (DTI) is critical for drug discovery. Existing methods often rely on single-modal representations (e.g.,
arXiv:2605.29489v1 Announce Type: new Abstract: Weight-space model merging is usually formulated as an algebraic operation on checkpoints, yet at LLM scale the limiting resource is often the set of ex
arXiv:2509.17208v3 Announce Type: replace Abstract: Machine-learned coarse-grained (CG) potentials are fast, but degrade over time when simulations reach under-sampled bio-molecular conformations, and
arXiv:2605.29791v1 Announce Type: new Abstract: While Large Language Models (LLMs) can convincingly simulate personas in explicit self-reports, they often deviate in implicit behavioral decisions, rev
arXiv:2605.29643v1 Announce Type: new Abstract: Cross-Video Reasoning (CVR) has emerged as a critical frontier in multimodal intelligence, requiring models to retrieve, align, and aggregate evidence d
arXiv:2602.23258v2 Announce Type: replace Abstract: While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information from individual agents. C
arXiv:2602.11760v2 Announce Type: replace-cross Abstract: Feature-importance methods show promise in transforming machine learning models from predictive engines into tools for scientific discovery. H
arXiv:2605.30038v1 Announce Type: cross Abstract: Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve ali
AlloyDB for PostgreSQL is a fully managed, PostgreSQL-compatible database service designed for the most demanding enterprise workloads. It combines the best of PostgreSQL with the power of Google, del
arXiv:2605.30140v1 Announce Type: new Abstract: Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot anomaly detection (AD) approaches have achieved impr
arXiv:2605.29535v1 Announce Type: new Abstract: Vision-Language Models (VLMs) process thousands of visual tokens per image alongside comparatively few text tokens, yet existing compression methods tre
arXiv:2605.29004v1 Announce Type: new Abstract: Reported retrieval scores for training-free shape descriptors conflate local signal design, normalization, aggregation, codebook fitting, and metric cho
arXiv:2602.02849v2 Announce Type: replace Abstract: The design of Analog and Mixed-Signal (AMS) integrated circuits remains heavily reliant on expert knowledge, with transistor sizing a major bottlene
arXiv:2605.29727v1 Announce Type: new Abstract: Block-diffusion drafters have recently emerged as a powerful alternative for speculative decoding by predicting multiple future-token distributions in a
arXiv:2605.29560v1 Announce Type: new Abstract: Parameterizing high-fidelity 'digital twins' of batteries is a critical yet challenging inverse problem that hinders the pace of battery innovation. Pre
arXiv:2605.28849v1 Announce Type: new Abstract: Gradient temporal-difference methods provide stable off-policy prediction with linear function approximation, but their practical performance is strongl
arXiv:2605.30231v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) often struggle with robust 3D spatial reasoning. Prevailing methods that rely on fine-tuning with 3D visual question-ans
arXiv:2602.12642v2 Announce Type: replace-cross Abstract: Reward-maximizing RL methods have shown to be capable of enhancing the reasoning performance of LLMs, but often lead to reduced generation div
arXiv:2605.28969v1 Announce Type: cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how f
arXiv:2605.29697v1 Announce Type: new Abstract: In Agentic Search, trajectory-level outcome rewards fail to quantify the behavioral contributions of individual steps, while existing step-level reward
arXiv:2605.29379v1 Announce Type: new Abstract: We present BrahmicTokenizer-131K, a 131,072-vocabulary byte-level BPE tokenizer that closes the Brahmic compression gap at the 131K-vocabulary class whi
arXiv:2601.01162v3 Announce Type: replace-cross Abstract: Qualitative data are widespread in domains such as healthcare, marketing, and bioinformatics, where clustering offers a fundamental tool for p
arXiv:2605.29008v1 Announce Type: new Abstract: Driving a system from one state to another through targeted interventions is a fundamental challenge in science, yet most predictive models offer limite
arXiv:2605.29836v1 Announce Type: cross Abstract: Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Id
arXiv:2408.15451v3 Announce Type: replace Abstract: While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversari
arXiv:2605.29742v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) for regulatory compliance demands rigorous traceability via comprehensive citations across multi-tiered authority
arXiv:2605.29935v1 Announce Type: cross Abstract: Autonomous driving systems are commonly trained and evaluated within limited geographic regions, which hinders their scalability when deployed in new
arXiv:2605.29607v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free
arXiv:2510.14150v5 Announce Type: replace Abstract: We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmi
arXiv:2604.06805v2 Announce Type: replace Abstract: Multi-step Chain-of-Thought (CoT) has significantly advanced the mathematical reasoning capabilities of LLMs by leveraging explicit reasoning steps.
arXiv:2604.01904v2 Announce Type: replace-cross Abstract: Data rights owners can detect unauthorized data use in large language model (LLM) training by querying with proprietary samples. Often, superi
arXiv:2605.30333v1 Announce Type: new Abstract: A plausible future mathematical claim must satisfy two constraints: it should follow the direction of prior work and respect the formal dependencies tha
arXiv:2605.29467v1 Announce Type: cross Abstract: Stacking probabilistic building blocks into deeper architectures typically breaks closed-form inference. We show that closed-form inference can be pre
arXiv:2605.29612v1 Announce Type: cross Abstract: Although large language model (LLM) based multi-agent systems (MAS) show their capability to solve complex tasks and achieve higher performance over s
arXiv:2605.28866v1 Announce Type: cross Abstract: Token-based time series large language models (TS-LLMs) have emerged as a promising direction for time series analysis and reasoning. However, prior s
arXiv:2510.01711v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained V
arXiv:2605.30000v1 Announce Type: new Abstract: Front-end web code has become a core product surface for every frontier LLM release, yet evaluating these interactive applications at development speed
arXiv:2605.29886v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves knowledge-intensive question answering by incorporating external evidence. However, existing RAG methods
arXiv:2502.03805v2 Announce Type: replace Abstract: Large language models have revolutionized natural language processing but face significant challenges of high storage and runtime costs, due to the
arXiv:2605.29786v1 Announce Type: new Abstract: Reproducibility is fundamental to the scientific method, yet remains a critical challenge in machine learning. Contributing factors include underspecifi
arXiv:2602.20176v2 Announce Type: replace-cross Abstract: D-peptide binders targeting L-proteins have promising therapeutic potential. Despite rapid advances in machine learning-based target-condition
arXiv:2605.30211v1 Announce Type: new Abstract: Self-supervised video Object-Centric Learning (OCL) aims to discover distinct objects and associate them across time, whereas self-supervised Multi-Obje
arXiv:2512.10659v3 Announce Type: replace Abstract: Outlier detection identifies data points that significantly deviate from the majority of the data distribution. Explaining outliers is crucial for u
arXiv:2605.29568v1 Announce Type: new Abstract: Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during seq
arXiv:2605.30215v1 Announce Type: new Abstract: Recent feed-forward 3D reconstruction transformers have scaled to over a billion parameters, following the broader trend of increasing model capacity in
arXiv:2605.29247v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underp
arXiv:2603.29954v2 Announce Type: replace Abstract: In this work, we tackle the problem of Open World Object Detection (OWOD). This challenging scenario requires the detector to incrementally learn to
arXiv:2605.30107v1 Announce Type: new Abstract: Creating spoken dialogue datasets is methodologically challenging, and these challenges are amplified when the goal is to build multilingual, multi-para
arXiv:2512.10401v3 Announce Type: replace-cross Abstract: This paper is concerned with differentiable resampling in the context of sequential Monte Carlo (e.g., particle filtering). Drawing on reparam
arXiv:2503.20897v2 Announce Type: replace Abstract: Semi-supervised domain generalization (SSDG) leverages a small fraction of labeled data alongside unlabeled data to enhance model generalization. Mo
arXiv:2605.30039v1 Announce Type: new Abstract: Large Language Models have demonstrated remarkable progress in general-purpose capabilities and can achieve strong performance in specific domains throu
arXiv:2602.00324v2 Announce Type: replace-cross Abstract: Synchronization over the special Euclidean group SE(3) aims to recover absolute poses from noisy pairwise relative transformations and is a co
arXiv:2510.27607v3 Announce Type: replace Abstract: Augmenting vision-language-action models (VLAs) with world models is promising for robotic policy learning but faces challenges in jointly predictin
arXiv:2605.29891v1 Announce Type: new Abstract: Recent Large View Synthesis Models (LVSMs) advocate an encoder-decoder architecture that separates reconstruction and rendering into distinct networks.