Knowledge catalogue
arXiv:2610.22355v1 Announce Type: new Abstract: Generative visual verifiers play a crucial role in advancing multimodal intelligence. To enhance the robustness of visual verifiers in complex multimoda
arXiv:2610.22200v1 Announce Type: new Abstract: Computer use has reached a turning point: the focus is expanding from GUI-only interaction to systems that complete tasks on users' computers through vi
Pay attention to this new wave of VLMs. Glimpse is the first model from @ElorianAI, the brains that led Google's Gemini and Apple's MM-1. Quick test: 10 game boards from an overhead camera. Same promp
arXiv:2610.21046v1 Announce Type: cross Abstract: Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate what a paper says. We introduce R
arXiv:2610.21390v1 Announce Type: cross Abstract: Multi-agent large language model (LLM) systems are increasingly deployed at the edge to support complex tasks that require collaboration and informati
arXiv:2610.22066v1 Announce Type: new Abstract: Given a state and a set of options, such as intents, tools or interface elements, System One decision models return a distribution over the options in o
arXiv:2610.20927v1 Announce Type: new Abstract: Long-horizon LLM agents rely on context compaction: when the interaction history outgrows the context window, a compressor replaces it with a natural-la
arXiv:2610.21040v1 Announce Type: new Abstract: Recursive Self-Improvement (RSI) has gained wide attention for its ability to work with limited data. In a proposer-solver loop, a proposer model writes
arXiv:2610.21539v1 Announce Type: new Abstract: Diffusion models (DMs) have steadily demonstrated outstanding performance in high-fidelity, controllable generation across diverse scenarios, following
arXiv:2610.21739v1 Announce Type: cross Abstract: As agents powered by foundation models move into open-ended environments, continual learning from experience becomes essential. For agents built on mo
arXiv:2610.22075v1 Announce Type: new Abstract: Recent work shows that depth recurrence can be retrofitted into pretrained language models. In this work, we adapt this paradigm for visual understandin
arXiv:2610.20811v1 Announce Type: new Abstract: Generative gameplay requires more than immediate responses to player actions.Actions should have persistent consequences, while the generated world shou
arXiv:2610.22198v1 Announce Type: cross Abstract: Safe multi-agent coordination typically assumes what real-world, deployed, resource-constrained robots cannot provide: continuous, perfect state shari
arXiv:2610.21682v1 Announce Type: cross Abstract: Reinforcement learning (RL) can become off-policy due to training-inference mismatch, mini-batch updates, and asynchronous training.The resulting mism
arXiv:2610.21518v1 Announce Type: new Abstract: Understanding how the human brain constructs meaning from real-world language remains a fundamental challenge, as semantics depend on context that varie
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:2610.20866v1 Announce Type: cross Abstract: Realistic traffic simulation and autonomous planning both depend on modeling interactions among heterogeneous road users whose dynamics, constraints,
arXiv:2610.20968v1 Announce Type: cross Abstract: Executing heavy-duty physical manipulation in unpredictable environments remains a major challenge for quadrupedal robots lacking dedicated manipulato
arXiv:2511.21414v2 Announce Type: replace Abstract: Deep neural networks (DNNs) and Kolmogorov-Arnold networks (KANs) are flexible function approximators, but their accuracy can require substantial ne
arXiv:2610.22192v1 Announce Type: new Abstract: Converting verifier outcomes into useful policy updates and partial progress into complete task resolution is crucial for terminal agents. We present Te
arXiv:2610.20901v1 Announce Type: cross Abstract: Task-Oriented Grasping (TOG) has emerged as an important skill for purposeful robotic manipulation. Given the task of using a knife to 'slice bread,'
arXiv:2610.21477v1 Announce Type: new Abstract: Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to fre
arXiv:2604.03376v2 Announce Type: replace Abstract: Current work on radiology report evaluation has focused primarily on LLM-based metrics for chest X-rays (CXR), leaving open whether such approaches
arXiv:2610.05373v2 Announce Type: replace Abstract: On-policy distillation (OPD) has emerged as an effective post-training paradigm for language models, with recent efforts extending it to block diffu
TL;DR -- Interpretability might be way more tractable than we thought, and the guy who helped convince everyone otherwise is now saying we can understand models by directly studying neurons and their
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:2610.21306v1 Announce Type: new Abstract: Vision-language-action (VLA) models transfer semantic knowledge acquired through vision-language pretraining to robot control, achieving strong performa
We’re excited to be day 0 partners for @reflection_ai’s first open-weight model! For a limited time, Beam is FREE on Ollama! In partnership with @reflection_ai this model is hosted in the US with full
arXiv:2610.20676v1 Announce Type: new Abstract: Correctness feedback suppresses the very evidence that specification-completeness auditing is designed to uncover: programs that satisfy a written contr
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:2610.20824v1 Announce Type: cross Abstract: Wolof is spoken by 23M people, mostly in Senegal, but remains weakly supported by open-weight language models, while API models raise cost, governance
arXiv:2503.14555v2 Announce Type: replace-cross Abstract: Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these
arXiv:2610.15788v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed as teams, yet they fail in characteristically social ways: information holders stay silent,
arXiv:2604.25083v2 Announce Type: replace Abstract: Computer Architecture research has traditionally required the exploration of vast, highly complex design spaces through manual human effort. Large L
arXiv:2610.19478v1 Announce Type: new Abstract: Agricultural systems make decisions over heterogeneous entity types, textual judgments, and knowledge-question options. Generating a textual answer adds
arXiv:2512.16245v2 Announce Type: replace Abstract: Merging large language models (LLMs) is a practical way to compose capabilities from multiple fine-tuned checkpoints without retraining. Yet standar
Amazing to see @AIatMeta launch the best US open-weight model so far! The model will be available on Ollama shortly. 🫡 Today we’re releasing Muse Spark Open, the most capable US open-weight model to d
arXiv:2610.20571v1 Announce Type: new Abstract: Long-form agentic video generation must turn a screenplay into shots that remain spatially and temporally consistent across nonconsecutive requests. Pas
arXiv:2610.16426v1 Announce Type: new Abstract: Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a classi
arXiv:2610.17206v1 Announce Type: new Abstract: We propose AutoMARS (Automatic Multi-Agent Risk Assessment), an agentic framework for automatic and scalable comparative risk assessment in supply chain
arXiv:2610.15995v1 Announce Type: cross Abstract: This paper presents AutoSec-RAN, a specification-grounded large language model (LLM) framework for automated security triage of Open Radio Access Netw
arXiv:2610.03998v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as synthetic personas representing survey respondents. Their validity as substitutes for particul
arXiv:2610.17827v1 Announce Type: new Abstract: Existing approaches to training and evaluating search agents focus heavily on final-answer quality, largely neglecting how generated answers map back to
arXiv:2603.16557v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However,
arXiv:2610.19685v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes. Matching a local reference distribution keeps t
arXiv:2610.16117v2 Announce Type: new Abstract: LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary
arXiv:2311.04902v3 Announce Type: replace Abstract: Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, which removes some model weights without hurting per
arXiv:2610.15634v1 Announce Type: new Abstract: Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contribu
arXiv:2610.19291v1 Announce Type: new Abstract: In so-called 'Industry 4.0,' integrated sensors, analytics tools, and other digital technologies supplement industrial workflows, potentiating enhanced
arXiv:2610.19021v1 Announce Type: new Abstract: Recent work has questioned whether large language models (LLMs) can be useful for temporal event prediction. Despite vast pretrained world knowledge, LL
arXiv:2610.18354v1 Announce Type: new Abstract: Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capabili
arXiv:2509.25266v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is rapidly reshaping educational practice, challenging long held assumptions about teaching and learning. This ar
arXiv:2610.20251v1 Announce Type: new Abstract: Boundary delineation of anatomical structures in prostate MRI is often compromised by regional ambiguity. Automated segmentation methods relying on glob
arXiv:2610.19610v1 Announce Type: new Abstract: Industrial anomaly detection (AD) is bottlenecked by the scarcity of anomalous samples, making high-fidelity anomaly synthesis crucial for improving dow
arXiv:2610.16191v1 Announce Type: new Abstract: A model may select the correct answer yet fail to construct it through a sequence of local decisions. We introduce Choice2Seq, a diagnostic benchmark th
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:2610.19157v1 Announce Type: cross Abstract: Code generation models are actively being used in professional and educational settings. However, the competence of large language models (LLMs) to ge
arXiv:2606.15251v2 Announce Type: replace-cross Abstract: Accurate and interpretable motion prediction for heterogeneous traffic spaces, including pedestrians, bicycles, cars, and trucks, is essential
arXiv:2610.19364v1 Announce Type: new Abstract: Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do n
Elon Musk says the central lesson of 2001: A Space Odyssey is that you should not make AI lie, because HAL killed the crew to reconcile two contradictory orders “But let me tell you how things can pot