Stories tagged science & research.
arXiv
arXiv:2509.05500v2 Announce Type: replace-cross Abstract: Autonomous microrobots could enable minimally invasive interventions in confined biological environments, but their operation requires real-time navigation among moving obstacles and environmental disturbances. Here we present a closed-loop…
arXiv
arXiv:2609.26145v1 Announce Type: new Abstract: A debate panel can become unanimous without becoming more correct. This is dangerous for downstream safeguards: a substituted verification ballot can change only narrow-margin votes, while richer arbiters lose disagreement as a natural targeting…
arXiv
arXiv:2609.26124v1 Announce Type: new Abstract: Despite the remarkable progress of LLM-based and knowledge graph-augmented Radiology Report Generation (RRG) methods, existing techniques still suffer from inherent defects. Conventional LLM-only models lack structured medical prior knowledge…
arXiv
arXiv:2607.13049v2 Announce Type: replace Abstract: Foundation models give robots powerful high-level reasoning, yet turning that intelligence into reliable physical action remains difficult: roboticists must still align device drivers, network interfaces, sensors, controllers, and safety…
arXiv
arXiv:2609.25891v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) often struggle with fine-grained visual perception when processing complete images, as critical evidence may only appear in local regions. On-policy self-distillation (OPD) enables transferring privileged…
arXiv
arXiv:2609.26095v1 Announce Type: new Abstract: With the growing global demand for energy, nuclear fusion has emerged as a promising direction for future clean energy. Tokamaks represent one of the leading approaches to magnetic-confinement fusion. Achieving high-performance, long-pulse, and…
arXiv
arXiv:2609.25960v1 Announce Type: new Abstract: When an agent handling a payment exception loses money, the agent-step attribution methods this paper compares against will name one of its actions. They will do so even when a settlement message was dropped and the agent never had a chance: they…
arXiv
arXiv:2609.26642v1 Announce Type: new Abstract: Successful agent execution need not identify which future product improvement its user would value. We present a decision-specific audit that maps a declared observation channel and product-value contrast to compatible intervals and witness…
arXiv
arXiv:2609.25804v2 Announce Type: new Abstract: LLM agents increasingly work on long-horizon tasks, and the decisions they make along the way, such as which hypothesis to test or which implementation to build on, determine the outcome of the whole run. Making these decisions well is becoming a key…
arXiv
arXiv:2609.25738v1 Announce Type: new Abstract: Omni-modal models have expanded multimodal interaction across vision, audio, speech, and language. However, their training is predominantly organized around semantic descriptions and general-purpose objectives, leaving physical attributes, interaction…
arXiv
arXiv:2609.26039v1 Announce Type: cross Abstract: Point cloud generation has emerged as a crucial task for accurately capturing and reproducing the complexity of the physical world. However, existing generative approaches, predominantly relying on Transformers and Variational Autoencoders (VAEs)…
arXiv
arXiv:2609.26355v1 Announce Type: cross Abstract: Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted mathematical definition, leaving its relationship to commonly used training signals unclear. We…
arXiv
arXiv:2609.25677v1 Announce Type: new Abstract: Marketers now deploy generative AI agents as synthetic consumers to pretest visual assets such as logos, packaging, and advertising at a fraction of human-panel cost. However, this procedure assumes that a model seeing a visual cue can also perceive…
arXiv
arXiv:2609.25607v1 Announce Type: new Abstract: Scientific papers keep much of their quantitative content in tables and supplementary files, where a number means something only through its header, caption, unit, analytical method, and the conventions of its field. Recovering the rows and columns of…
arXiv
arXiv:2609.25572v1 Announce Type: new Abstract: LLM-based user simulators aim to bridge the offline-online gap in recommender evaluation by emulating users through injected traits, where preference attributes determine what a user engages with and a behavioral activity trait governs how long they…
arXiv
arXiv:2609.25491v1 Announce Type: new Abstract: In this paper, we examine speech datasets for their inclusion of LGBTQIA+, or queer, voices and provide a taxonomy of tensions to better understand why there is a lack of such voices in current speech technology datasets. Through an audit of six…
arXiv
arXiv:2609.26679v1 Announce Type: cross Abstract: In grokking an early fit to the training data separates from a much later improvement in generalization. During this delay, training can move from a fixed neural tangent kernel (NTK) regime to one in which task-relevant kernel eigendirections…
arXiv
arXiv:2609.26361v1 Announce Type: cross Abstract: With the rapid pace of AI research and the hundreds of daily new publications, staying up-to-date with the latest developments has become increasingly difficult. For researchers, quickly identifying impactful work is essential, yet manually…
arXiv
arXiv:2609.25463v1 Announce Type: new Abstract: Reasoning-oriented reinforcement learning enables large language models to solve mathematical, coding, and other multi-step tasks, but shifts a substantial portion of the training cost to rollout, where trajectories are generated for policy updates…
arXiv
arXiv:2609.11873v3 Announce Type: replace-cross Abstract: Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal…
arXiv
arXiv:2609.25773v1 Announce Type: cross Abstract: HopChain has shown on still images that multi-hop data synthesis improves vision-language reasoning, because long chain-of-thought reasoning exposes errors that compound across steps, while most data used for reinforcement learning with verifiable…
arXiv
arXiv:2605.00915v2 Announce Type: replace-cross Abstract: Probing frozen vision transformers typically uses permutation-invariant aggregation (GAP or $\texttt{[CLS]}$), treating patch tokens as an unstructured set. Content-dependent probes such as self-attention are useful accuracy controls, but…
arXiv
arXiv:2609.25876v1 Announce Type: cross Abstract: The connection between the Kolmogorov-Arnold representation theorem (KART) and neural network design has led to the development of Kolmogorov-Arnold Networks (KANs), with applications ranging from STEM problems to AI tasks. In this paper, we…
arXiv
arXiv:2606.14157v2 Announce Type: replace-cross Abstract: Cities deliver basic services through mixed public-private facility networks, including schools, clinics, transit providers, and subsidized service points. In these systems, planners often observe where households go, but not the latent cost…
arXiv
arXiv:2607.18496v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for a range of software, hardware and human-centered security tasks. Consequently, LLM performance on security tasks is an active area of measurement and research, often with a focus on…
arXiv
arXiv:2609.26486v1 Announce Type: cross Abstract: Automatic lip-synchronous dubbing requires a speech synthesis model to generate alternating voice and silence patterns in the target language that match the timing of the source clip precisely to ensure an optimal viewing experience. Prior works…
arXiv
arXiv:2510.17830v3 Announce Type: replace-cross Abstract: Inertial fusion energy promises nearly unlimited, clean power if it can be achieved. However, the design and engineering of fusion systems requires controlling and manipulating matter at extreme energies and timescales; the shock physics and…
arXiv
arXiv:2609.25788v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) promise a paradigm shift toward zero-shot forecasting by eliminating task-specific training. However, existing works often overlook trade-offs between predictive accuracy and probabilistic calibration. This…
arXiv
arXiv:2609.25542v1 Announce Type: cross Abstract: Corporate default prediction is a core problem in financial risk management, yet traditional credit models rely heavily on financial statements that are often sparse or unavailable for many firms. Corporate transaction networks offer a complementary…
arXiv
arXiv:2609.25052v1 Announce Type: cross Abstract: "An agent that writes its conclusions into a store it later retrieves from closes a loop usually reported as one-way contamination. Taking the loop to the infinite-tenure limit against an append-only store gives a different picture: because writing…