Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2609.14178v1 Announce Type: new Abstract: The rapid diffusion of hate speech and misinformation on social networks challenges democratic societies, since direct suppression efforts may deepen p...
arXiv:2609.14779v1 Announce Type: new Abstract: Performing deliberate mathematical reasoning in visual contexts is a hallmark of advanced Multimodal Large Language Models (MLLMs) and requires a sophi...
arXiv:2609.14963v1 Announce Type: new Abstract: As large language models become capable translators of classical texts, a key challenge is deciding which outputs need expert review when no human refe...
arXiv:2609.15938v1 Announce Type: new Abstract: Scientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing new explanations. Recent systems com...
arXiv:2504.07825v2 Announce Type: replace Abstract: Commonsense reasoning is a key language model capability, as it is purportedly a prerequisite for many basic tasks, unlike specific factual knowled...
arXiv:2606.30943v2 Announce Type: replace Abstract: Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between the...
arXiv:2609.06327v2 Announce Type: replace-cross Abstract: A query-oblivious coreset for a softmax-attention head is a subset of the key-value pairs whose attention output is within $\varepsilon$ of t...
arXiv:2609.13251v1 Announce Type: new Abstract: Commercial and advertising images are frequently affected by poor framing, partially cropped subjects, truncated text or logos, and insufficient contex...
arXiv:2609.14473v1 Announce Type: new Abstract: Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical...
arXiv:2606.29997v2 Announce Type: replace Abstract: Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limi...
arXiv:2609.15863v1 Announce Type: new Abstract: Video diffusion models are stochastic and hard to control: precise content often requires repeated sampling without guaranteed success, and long-horizo...
arXiv:2609.15392v1 Announce Type: cross Abstract: Recent progress in image and 3D scene generation has enabled increasingly realistic static environments, yet most methods remain confined to such sta...
arXiv:2512.20257v2 Announce Type: replace Abstract: With the rise of easily accessible generative tools for creating and manipulating multimedia content, the threat of realistic synthetic alterations...
arXiv:2603.25175v2 Announce Type: replace Abstract: Monocular egocentric 3D pose estimation is difficult because severe foreshortening, self-occlusion, and a restricted field of view often remove the...
arXiv:2606.00751v2 Announce Type: replace Abstract: Visual Speech Recognition (VSR) aims to recognize speech from visual cues such as lip movements. Still, its performance is fundamentally limited by...
The paper explores pre‑training methods for graph transformers applied to biochemistry. It finds that supervised pre‑training with computed property labels yields the best improvement on downstream tasks, and it emphasizes that limiting model capacity helps prevent overfitting.
PhysBrain 1.5 is a unified vision‑language model that learns to understand physical environments, generate actions, and predict future states by encoding language, end‑effector motion, and dense visual targets as discrete sequences and training them with autoregressive next‑token prediction. The model is pre‑trained on human interaction videos and fine‑tuned on human demonstrations, robot trajectories, and simulated experience, achieving an average score of 72.5 across 28 embodied understanding benchmarks and outperforming other open‑source models on 14 of them. It also demonstrates the ability to produce end‑effector trajectories and predict future scenes with spatially aligned RGB, depth, and robot‑mask outputs.
The paper investigates whether large language model (LLM) agents can autonomously manage long‑horizon physical tasks without human intervention. It proposes a multi‑agent framework that combines planning, tool calling, observation, and verification, and tests it on agricultural tasks under varying weather conditions. Results show that zero‑shot LLM agents match reinforcement learning (RL) agents in the same environment and outperform RL when the environment shifts, suggesting a viable path for self‑adaptive physical AI.
UniCAR‑RL is an annotation‑free reinforcement learning framework designed to improve multimodal large language models’ visual mathematics reasoning. It decouples perception and reasoning by using three branches: Caption‑RL for perception optimization, Reasoning‑RL for logical reasoning with a gold image description, and QA‑RL for end‑to‑end question answering. Experiments show significant gains in mathematical and visual reasoning across various model architectures and scales using only raw short‑answer data.
DynSTEER is a dynamic stage‑wise trajectory evaluation framework designed for large language model agents performing long‑horizon tasks. It segments rollouts into stages anchored by key actions, uses a path‑tolerant milestone graph to accommodate diverse valid strategies, and adaptively routes queries to multi‑tier judges while halting unrecoverable executions early. Experiments show it improves evaluation discriminability by 85.2% over native methods, separates all model pairs with statistical significance, and saves 34.51% of execution steps on failed rollouts.