Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2609.36965v1 Announce Type: new Abstract: System One models such as Jev offer an efficient alternative to generative language models for tasks that require decisions rather than open-ended resp...
arXiv:2609.37408v1 Announce Type: new Abstract: Narrative extraction allows us to identify online hate narratives, supporting the construction of rigorous detection systems. Existing computational ap...
arXiv:2609.37498v1 Announce Type: new Abstract: Wikipedia aims to provide a unified, neutral record of history, yet its independent language editions often function as distinct epistemic communities,...
arXiv:2609.37533v1 Announce Type: new Abstract: Masked diffusion models (MDMs) generate sequences by progressively unmasking several tokens per denoising step, but their reverse process is typically...
arXiv:2509.23140v2 Announce Type: replace Abstract: Recent advancements have endowed Large Language Models with impressive general reasoning capabilities. However, these reasoning models often perfor...
arXiv:2605.28013v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vi...
arXiv:2609.36145v1 Announce Type: new Abstract: Tampered Text Detection (TTD) is essential for safeguarding document authenticity in security-critical workflows. Existing expert models are effective...
arXiv:2609.36374v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models have achieved impressive performance by scaling model and dataset size, but their cost excludes most research gro...
arXiv:2609.36648v1 Announce Type: new Abstract: Vision-language pre-training has reshaped image clustering, giving rise to language-assisted image clustering (LaIC), which leverages textual semantics...
arXiv:2609.37263v1 Announce Type: new Abstract: While Large Vision-Language Models (LVLMs) achieve remarkable success, hallucinations remain a significant barrier to their reliable deployment. Recent...
arXiv:2609.37407v1 Announce Type: new Abstract: While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a ma...
arXiv:2607.28225v2 Announce Type: replace Abstract: Agentic vision-language models (VLMs), which interleave textual reasoning with explicit tool calls such as cropping and code-based image manipulati...
The study examines how reader proficiency influences the relationship between layer-wise surprisal from large language models (LLMs) and eye-tracking gaze measures. Using the MECO L2 corpus, researchers compared high- and low-proficiency readers on first-pass gaze duration (FPGD) and total gaze duration (TGD), finding that lower-proficiency readers exhibit deeper Predictive Depth for FPGD, while TGD shows deeper Predictive Depth across both groups. The results suggest that the distribution of predictive power across LLM layers relates to the timing and breadth of reading processes and varies with reader proficiency.
The paper proposes Layer-Informed Fine-Tuning (LIFT), a method that identifies and updates only the most functionally critical layers of large language models (LLMs) using a bottleneck identification mechanism based on sensitivity analysis. By focusing on layers that handle conceptualization, reasoning, and textualization, LIFT aims to accelerate training and enhance performance on reasoning tasks. Experiments demonstrate that this selective fine-tuning approach both speeds up the training process and yields significant performance gains.
The paper introduces a surrogate modeling framework that combines a Variational Autoencoder with a convolutional or graph basis to reduce dimensionality, and propagates the resulting latent vector over time using a Temporal Fusion Transformer. This approach captures both long‑range and short‑range dynamics while supporting static covariates, and it has been validated on three distinct systems, matching full simulation results at a fraction of the computational cost. The method also offers built‑in uncertainty quantification, enabling targeted experimental design and adaptability to new systems.
The paper introduces a framework for evaluating large language model agents by attempting to end‑to‑end reproduce published astronomy studies, separating execution from verification and distinguishing computational failures from methodological ambiguities. Applying this to fourteen papers—one from The Astrophysical Journal and thirteen from Nature—revealed that eleven contained ambiguities that prevented a uniquely specified reproduction path. In a controlled case study, twelve different analysis paths produced distance estimates ranging from 2.16 to 3.53 kpc, with only one matching the published value of ~2.70 kpc, demonstrating that matching outcomes does not guarantee that the agent has reconstructed the underlying reasoning. whyItMatters":"The study shows that end‑to‑end reproduction can expose gaps in implicit scientific knowledge within AI systems, highlighting the need for better integration of causal relevance in LLM agents."
The paper introduces Solver Agent, an AI framework that uses large language models to perform calculations and proofs in mathematics and theoretical physics, tracking the solution process via a persistent ledger. It applies this framework to study global F‑theory uplifts of Type IIB orientifolds and S‑folds, establishing conditions for Weierstrass models over projective threefolds with terminal ζ_k quotient singularities to yield Ε-factorial elliptically fibered Calabi‑Yau fourfolds. The authors derive fixed‑point contributions to Hodge data and Euler characteristics, demonstrate how these corrections determine localized D3‑brane charges for tadpole cancellation, and illustrate the results with toric hypersurface constructions and methods for four‑form flux analysis in Δ=1 compactifications.
AerialDojo-200K is a large-scale benchmark suite for open-world aerial object-goal search, featuring 42 simulation scenes across four families and 21 types, including urban, natural, infrastructure, and disaster environments. The dataset contains 205,732 task instances—over 100K semantic-goal and over 100K image-goal tasks—each with a collision-free reference trajectory and multi-view video recordings. A unified evaluation framework splits scenes into 21 in-distribution and 21 out-of-distribution sets, and preliminary tests on multimodal large language models show significant room for improvement in general-purpose aerial agents.
The paper introduces GLIME, a lifelong model editing framework that integrates knowledge editing with preference optimization to handle continual updates in large language models. GLIME employs replay-based editing and a gradient constraint to prevent overfitting to target prompts and preserve previously edited knowledge. Experiments demonstrate that GLIME enhances knowledge generalization while maintaining editing performance and overall model capabilities.
The paper investigates where and how large language models encode signals that indicate answer correctness. By examining hidden states, token probabilities, residual-stream features, attention, and their combinations, the authors find that correctness signals are concentrated in the answer span and that different signal families complement each other. Fusing these signals improves robustness, especially under distribution shifts, and can be used to control retrieval in downstream tasks.