Knowledge catalogue
arXiv:2610.21424v1 Announce Type: new Abstract: Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Repres
arXiv:2610.20989v1 Announce Type: cross Abstract: Improving the reasoning capabilities of vision-language models (VLMs) often relies on post-training with supervision from stronger models. Two common
arXiv:2610.21182v1 Announce Type: new Abstract: Latent chain-of-thought replaces written reasoning steps with continuous hidden states, giving models additional steps to compute before answering. It r
arXiv:2610.21713v1 Announce Type: cross Abstract: Language embeddings are increasingly used in recommenders to represent item content, but their privacy risks remain poorly understood. We study whethe
arXiv:2610.21250v1 Announce Type: new Abstract: Multi-teacher on-policy distillation enables rectified-flow models with diffusion-transformer architectures to combine task-specific capabilities within
arXiv:2610.21165v1 Announce Type: new Abstract: Long-context capability has become essential for large language models (LLMs) to handle complex tasks, yet continuously expanding the context window doe
arXiv:2610.21767v1 Announce Type: new Abstract: Can AI agents organize scientific investigations that lead to well-supported conclusions? To evaluate this capability, we introduce PhysClosureBench, a
arXiv:2610.22196v1 Announce Type: new Abstract: External-memory systems extend language-model applications beyond a context window, but their quality depends critically on the model executing the writ
arXiv:2610.22289v1 Announce Type: new Abstract: Stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We inves
arXiv:2610.21412v1 Announce Type: new Abstract: Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large
arXiv:2610.22300v1 Announce Type: cross Abstract: Not all facts a language model can recall support further learning equally well. We distinguish active facts, which support generalization beyond thei
arXiv:2610.22280v1 Announce Type: new Abstract: Computer-use agents increasingly tackle long-horizon tasks, where running a frontier model at every step is expensive and a small open-weight model alon
arXiv:2610.21492v1 Announce Type: new Abstract: Language-model agents can accumulate interaction feedback, but reliably turning that feedback into reusable experience remains challenging. Existing met
arXiv:2602.18891v2 Announce Type: replace-cross Abstract: Advances in large language models (LLMs) are rapidly transforming scientific work, yet empirical evidence on how these systems reshape researc
arXiv:2507.09227v2 Announce Type: replace-cross Abstract: Interest in generating realistic synthetic medical images has grown in recent years. Such datasets can mitigate the scarcity of public data fo
arXiv:2610.20881v1 Announce Type: new Abstract: While foundation models and vision transformers (ViTs) have redefined visual representations, current active learning (AL) strategies for these backbone
arXiv:2610.21200v1 Announce Type: new Abstract: Protein foundation models increasingly support the generation of novel biological sequences, yet their reliance on large public datasets creates opportu
arXiv:2610.20761v1 Announce Type: new Abstract: Representation alignment improves and accelerates diffusion training by encouraging intermediate features to match a pretrained visual encoder. However,
I was running Unsloth IQ4_XS for a while and while it provided me with a healthy 96K context on 20GB vram, I did notice all the issues it had during draft and all the time and local tokens wasted tryi
arXiv:2610.22178v1 Announce Type: cross Abstract: We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data that sets a new Pareto frontier between performance
arXiv:2610.21029v1 Announce Type: cross Abstract: As autonomous agents become widely deployed, coordinating access to shared computing resources and services will become increasingly important. Recent
arXiv:2610.22029v1 Announce Type: cross Abstract: Self-evolving language models train on tasks they generate, so every round must decide which updated model the next round inherits. Current loops such
arXiv:2610.21950v1 Announce Type: cross Abstract: Tabular foundation models based on prior-data fitted networks (PFNs) predict on a new data set in a single forward pass, but they cannot report which
arXiv:2610.21795v1 Announce Type: new Abstract: Sky-image irradiance forecasting is dominated by a two-stage design: a video-prediction model forecasts future sky frames, and a separately trained regr
arXiv:2610.20822v1 Announce Type: new Abstract: Text-to-video models often generate the visual concepts requested in natural language prompts but fail to satisfy their intended ordering, timing, and p
arXiv:2610.21132v1 Announce Type: new Abstract: Pedestrian trajectory prediction holds significant applications across autonomous driving, intelligent surveillance, and smart cities. However, the comp
arXiv:2610.21363v1 Announce Type: cross Abstract: Test-time scaling can improve the performance of large language models by generating multiple answers to a question and aggregating them. Weighted ens
arXiv:2610.20964v1 Announce Type: cross Abstract: Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis
arXiv:2610.20003v2 Announce Type: replace Abstract: Human supervisors rely on coding agents' reports to assess progress, verify repairs, and decide when to intervene. But a supervisor cannot investiga
arXiv:2610.21128v1 Announce Type: cross Abstract: Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an impl
arXiv:2610.16717v2 Announce Type: replace Abstract: Does a large language model have a self, and if so, of what kind? We separate two functional levels familiar from biology: a self-index, which disti
arXiv:2610.19999v1 Announce Type: new Abstract: Legal-content reproduction requires matching the source exactly in section hierarchy, verbatim text, citations, and amendment spans; a dropped citation
arXiv:2604.03925v2 Announce Type: replace Abstract: Large language models (LLMs) struggle to accumulate evidence across multiple rounds of user interactions, failing to update their beliefs in a manne
arXiv:2610.14823v1 Announce Type: cross Abstract: Artificial intelligence is increasingly used to support product management tasks. At the same time, AI-native research and development (R&D) may incre
arXiv:2610.18090v1 Announce Type: new Abstract: Ambiguous or incomplete task specifications complicate both execution and clarification for language-model agents. Yet agents' responses to these inform
arXiv:2610.18240v1 Announce Type: new Abstract: Multi-agent debate (MAD) aims to improve large language model reasoning by exposing agents to alternative solutions and enabling iterative revision. How
arXiv:2601.20875v3 Announce Type: replace-cross Abstract: Governments and development partners often seek Sustainable Development Goal (SDG) 'accelerators' whose progress can propagate gains across hu
arXiv:2602.08519v2 Announce Type: replace Abstract: Attributed Graph Clustering (AGC) is a fundamental unsupervised task that integrates structural topology and node attributes to uncover latent patte
arXiv:2610.15153v1 Announce Type: new Abstract: We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill. The keep-alive duty is i
arXiv:2610.15008v1 Announce Type: new Abstract: Language models are frequently aligned to human preferences via imperfect evaluators whose errors can be exploited during optimization. We train policie
arXiv:2610.18105v1 Announce Type: new Abstract: Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems. Yet, its reliability remains poorly understood. We attr
arXiv:2603.26030v2 Announce Type: replace Abstract: In practical structural design and solid mechanics simulations, material properties inherently exhibit random variations within bounded intervals. H
arXiv:2610.14136v2 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with noi
arXiv:2610.18879v1 Announce Type: new Abstract: Protein function annotation operates over an expanding label space, making class-incremental learning (CIL) a natural framework for incorporating newly
arXiv:2610.19206v1 Announce Type: new Abstract: While work on LLM-based regression has largely focused on scalar prediction, multi-output text regression remains less explored. We present DualView, a
arXiv:2610.16402v1 Announce Type: new Abstract: Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily e
arXiv:2610.16301v1 Announce Type: new Abstract: Self-attention assigns two functions to one mechanism-where to read and how to mix-at the price of O(L^2) training, an O(T) decode state, and position s
arXiv:2610.19564v1 Announce Type: new Abstract: A spatial answer depends on the reference frame specified in language and its supporting visual evidence. Item accuracy alone obscures whether correctne
arXiv:2610.15236v1 Announce Type: cross Abstract: Condensed matter stands to gain profoundly from widespread adoption of artificial intelligence (AI). However, its current means of data organization i
arXiv:2610.18126v1 Announce Type: new Abstract: Freshness shapes an LLM decision at the moment it is made; the action it commits to is latent, carried out later, in a changing world. We therefore intr
arXiv:2610.19420v1 Announce Type: cross Abstract: Simulated environments enable scalable training data generation for embodied agents, but more data does not necessarily provide what a particular agen
arXiv:2506.23101v2 Announce Type: replace-cross Abstract: Ensuring the trustworthiness of Multimodal Large Language Models (MLLMs) requires rigorous evaluation of gender bias, particularly in socially
arXiv:2610.20417v1 Announce Type: new Abstract: Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures ac
arXiv:2610.19687v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in language models, but scalar outcomes provide coarse supervision over respo
arXiv:2610.18201v1 Announce Type: cross Abstract: Soil organic carbon (SOC) is an indicator of agricultural soil condition and carbon storage, but numerical outputs from large language models (LLMs) r
arXiv:2610.14960v1 Announce Type: cross Abstract: Can an autonomous AI agent reverse engineer a binary as well as a skilled human analyst? Do they adopt the same strategy, and can agents scale to real
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:2610.19571v1 Announce Type: new Abstract: Real-world engineering drawings are often large-format and information-dense. Answering practical engineering questions therefore requires both fine-gra
arXiv:2610.20027v1 Announce Type: cross Abstract: Linters are widely used in code maintenance and real-time IDE editing to surface lint alerts related to performance, style, error-prone, and other pat
arXiv:2601.02978v3 Announce Type: replace-cross Abstract: Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models