Stories tagged science & research.
arXiv
arXiv:2604.16548v3 Announce Type: replace-cross Abstract: The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, characterized by three properties: persistence, statefulness…
arXiv
arXiv:2605.08426v3 Announce Type: replace-cross Abstract: Ensuring that AI agents behave safely and beneficially when interacting with other parties has emerged as one of the central challenges of modern AI safety. While mechanism design, as the theory of designing rules to align individual and…
arXiv
arXiv:2609.15100v2 Announce Type: replace-cross Abstract: An image tool can change its underlying generator while retaining its public name, making version attribution from online posts ambiguous. We study this problem after the ChatGPT Images 2.5 launch. Our frozen collection contains 3,478 images…
arXiv
arXiv:2609.19855v2 Announce Type: replace-cross Abstract: Geographic applications need every object inside a radius that satisfies a semantic threshold, yet embedding indexes return approximate top-ranked lists and may omit qualifying records silently. We present FRESH-GEORANGE, a semantic- spatial…
arXiv
arXiv:2609.15638v2 Announce Type: replace Abstract: This study explores the use of deep learning and explainable artificial intelligence to diagnose hepatocellular carcinoma (HCC) and define effective biomarkers across five different stages of disease development using a transcriptomic biomarker…
arXiv
arXiv:2609.24259v2 Announce Type: replace-cross Abstract: The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over its response. Yet this capability has remained largely overlooked. To assess this…
arXiv
arXiv:2608.27785v2 Announce Type: replace-cross Abstract: We study audio-visual conflict as a compositional generalization test for AV-LLMs: the model must combine synchronized but semantically incompatible audio and video evidence and decide whether the pair matches. On VideoLLaMA 2-7B-AV, three…
arXiv
arXiv:2609.03480v3 Announce Type: replace-cross Abstract: We map tree species across Denmark using National Forest Inventory plots and EO data, while evaluating the potential of foundation models for large-scale forest characterization. We compare two alternative input representations for tree…
arXiv
arXiv:2609.12278v2 Announce Type: replace-cross Abstract: World models let agents plan by predicting the consequences of their actions, but changes in the environment can make them inaccurate. We study the problem of adapting a world model to an unknown test-time environment, drawn from a known…
arXiv
arXiv:2609.22332v2 Announce Type: replace-cross Abstract: Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act. Action-labeled robot videos directly supervise control but are costly and limited in…
arXiv
arXiv:2609.24424v2 Announce Type: replace-cross Abstract: Monocular RGB-based hand pose estimation has emerged as a critical research frontier in computer vision. The local hand pose estimation methods predict hand poses relative to the wrist, while global hand pose estimation also requires…
arXiv
arXiv:2609.24815v3 Announce Type: replace-cross Abstract: Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators require labor-intensive construction. We present Uranus, a…
arXiv
arXiv:2608.25286v2 Announce Type: replace Abstract: Artificial intelligence (AI) promises to accelerate biological research by automating computational analyses. Yet the ability of AI agents to execute on computational biology at the scale of complete research studies has not been systematically…
arXiv
arXiv:2412.03800v2 Announce Type: replace-cross Abstract: Reinforcement learning agents depend on reward signals whose density is rarely under the designer's control, and when such signals are absent, an agent must generate its own drive to explore. State entropy maximization offers a principled…
arXiv
arXiv:2607.20491v3 Announce Type: replace Abstract: A financial agent can repeat a decision while changing the work behind it. DFAH-Bench operationalizes the Determinism--Faithfulness Assurance Harness (DFAH), pairing decision agreement with tool-path agreement on the same qualified replays, then…
arXiv
arXiv:2606.06448v2 Announce Type: replace Abstract: LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to persistently store, retrieve, and update their own memory across sessions. A…
arXiv
arXiv:2609.24012v2 Announce Type: replace Abstract: Validation of generative social simulators often stops at face validity: emergent network structure is compared descriptively, without quantified parameter uncertainty or an adequacy check. We present an adequacy-aware calibration protocol that…
arXiv
arXiv:2512.16953v3 Announce Type: replace Abstract: Recognizing similarities among entities is central to both human cognition and computational intelligence. Within this broader landscape, Entity Set Expansion is one prominent task aimed at taking an initial set of (tuples of) entities and…
arXiv
arXiv:2402.03164v2 Announce Type: replace Abstract: Representing time is crucial for cyber-physical systems and has been studied extensively in the situation calculus. The most commonly used approach represents time by adding a real-valued function $\mathit{time}(a)$ that attaches a time point to…
arXiv
arXiv:2609.08016v2 Announce Type: replace Abstract: Multi-agent debate, in which several LLMs exchange arguments before producing an answer, is widely assumed to improve answer quality by surfacing genuine disagreement. That disagreement is hard to verify, and no single signal can settle it, so we…
arXiv
arXiv:2609.26749v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to the automated repair of C/C++ security vulnerabilities, and compile rate is a commonly reported proxy for progress: whether the generated patch compiles. We argue that compile rate is a…
arXiv
arXiv:2609.26704v1 Announce Type: cross Abstract: Large language models increasingly tackle hard reasoning problems by spending more test-time compute, yet the dominant strategy remains naive repeated sampling: draw many independent solutions and hope one is correct. Because such sampling explores…
arXiv
arXiv:2608.07066v2 Announce Type: replace Abstract: Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete because recurrent membrane states are commonly retained in floating point even after weight quantization. Quantizing these…
arXiv
arXiv:2609.26184v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into robotic control systems is enabling a new generation of autonomous agents capable of complex reasoning and planning. While this paradigm shift accelerates progress, it also introduces novel…
arXiv
arXiv:2609.26151v1 Announce Type: cross Abstract: Image restoration is inherently challenging due to the diverse and highly input-dependent nature of real-world degradations. While recent architectures like Transformers and state-space models have advanced the field, they predominantly rely on…
arXiv
arXiv:2607.16900v3 Announce Type: replace Abstract: Training agents that generalize to unseen, stateful environments requires a massive dataset of state-changing trajectories covering a vast and diverse set of APIs. However, scaling this broad supervision is severely bottlenecked by the immense…
arXiv
arXiv:2609.25721v1 Announce Type: cross Abstract: Language models are increasingly trained on the outputs of other models, forming chains that we call lineages, in which a trait present in one generation can pass to the next. Prior work on subliminal learning has shown that a teacher's trait can…
arXiv
arXiv:2609.25634v1 Announce Type: cross Abstract: We trained 64 independently seeded networks in four configurations, continuing each to sustained convergence or a 40,000-epoch ceiling. We then asked whether an RSB-inspired distribution of pairwise weight overlaps changes across the grokking…
arXiv
arXiv:2609.26603v1 Announce Type: cross Abstract: Hierarchical latent communication improves the generalization of a multi-grid power-flow model to new operating scenarios. The module exchanges information through two reduced graphs within a GENCO-based corrective network. We compare Kron-derived…
arXiv
arXiv:2609.25541v1 Announce Type: cross Abstract: Tabular foundation models learn to predict cell values in context, whereas world-model self-supervision asks for prediction in representation space (LeCun, 2022; Assran et al., 2023). On a tabular foundation-model prior, the latent term of a…