Knowledge catalogue
arXiv:2610.05303v1 Announce Type: new Abstract: A large language model (LLM) agent solves long-horizon tasks through many reasoning-action turns, with one verification signal at termination. Deployed
arXiv:2610.05996v1 Announce Type: new Abstract: Latent world models based on Joint-Embedding Predictive Architecture (JEPA) are deterministic by design. While successful in fully observable scenarios,
arXiv:2610.03980v1 Announce Type: new Abstract: Text-to-video (T2V) diffusion models can reproduce copyrighted, violent, or explicit content, which motivates concept erasure: removing designated conce
arXiv:2610.06080v1 Announce Type: cross Abstract: Gaussian-process limits are powerful in describing overparameterized machine learning models, yet their validity in structured tensor-network architec
arXiv:2610.06805v1 Announce Type: new Abstract: Long-horizon planning with latent world models requires reasoning across timescales and levels of abstraction. Existing task-agnostic JEPA world models
arXiv:2610.04238v1 Announce Type: cross Abstract: Humanoid robots could transport payloads substantially heavier than themselves by pulling passive wheeled vehicles instead of carrying the load. This
arXiv:2606.14737v2 Announce Type: replace-cross Abstract: Modern protein representation models support tasks such as enzyme design and drug discovery, but their reliance on static data such as sequenc
arXiv:2610.04249v1 Announce Type: new Abstract: Recent successes of matrix- and curvature-based optimizers have renewed interest in how update geometry shapes learning. These methods normalize or prec
arXiv:2610.04850v1 Announce Type: new Abstract: Protein binding prediction is central to target identification, therapeutic binder design, and large scale screening, yet remains challenging because bi
arXiv:2610.05768v1 Announce Type: cross Abstract: We ask: given a retrieved source audio S and a separate reference audio R, can we synthesize novel audio Y out of this pair (S,R) such that Y remains
arXiv:2610.06344v1 Announce Type: new Abstract: In deep graph neural networks, increasing depth enlarges the receptive field but often leads to over-smoothing, where node representations tend to align
arXiv:2610.05456v1 Announce Type: cross Abstract: In Networked Markov Decision Processes, transition dynamics are often unknown and the state--action space grows rapidly with the number of agents. In
Octop is an open-source, self-hosted AI assistant. Through its multi-agent architecture, it builds an intelligent environment that is both independent and collaborative for teams, families, and indivi
arXiv:2610.06594v1 Announce Type: new Abstract: Feed-forward visual geometry transformers such as VGGT reconstruct dense 3D structure from images in a single forward pass, simplifying multi-view 3D re
Banger paper from Microsoft and colleagues. If you run agents that search a large document collection, this one is worth your time. (bookmark it) They introduce CorpusMap, which resolves recurring ent
arXiv:2610.03014v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly connect model-generated decisions to security-sensitive software capabilities such as command exe
arXiv:2610.02299v1 Announce Type: cross Abstract: We introduce Psi-Resilience, a model-free feature importance method that derives explanations directly from the data itself via 1D topological signals
I use ChatGPT a lot. Probably a lot more than is reasonable. I read David Robinson’s Atlantic piece today about leaving OpenAI and his criticism of its culture of trial-and-error / “iterative deployme
arXiv:2610.01942v1 Announce Type: new Abstract: Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of
arXiv:2610.01884v1 Announce Type: new Abstract: We introduce an approach for collection-grounded B-roll sequence generation. Given a user's video collection, a directive given in natural language, and
arXiv:2610.00354v1 Announce Type: cross Abstract: AI agents that control wallets read attacker-reachable content, so they can be steered into proposing harmful transactions. The usual last line of def
arXiv:2610.01728v1 Announce Type: cross Abstract: Understanding loss landscapes is central to explaining neural-network training, yet their structure remains only partially understood even in simple m
arXiv:2610.00093v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from
arXiv:2610.00878v1 Announce Type: cross Abstract: General-purpose embodied robots should support both navigation toward language-specified destinations and dynamic person tracking under arbitrary init
arXiv:2609.39402v1 Announce Type: new Abstract: Value-model-free RLVR methods such as GRPO assign uniform advantages to all tokens in a rollout, ignoring that tokens contribute unequally. Recent metho
arXiv:2609.38983v1 Announce Type: cross Abstract: Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a
arXiv:2609.39561v1 Announce Type: cross Abstract: Abductive learning combines neural perception with symbolic reasoning, using explanations generated by abduction to supervise the perception model. Mu
arXiv:2609.35356v2 Announce Type: replace Abstract: Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted gene
arXiv:2609.38385v1 Announce Type: new Abstract: Supervised fine-tuning of discrete diffusion language models masks some response tokens and trains the model to recover their original values from the v
arXiv:2609.39352v1 Announce Type: cross Abstract: LLM agents increasingly rely on reusable Skills for complex, multi-step tasks, creating a critical supply-chain attack surface where poisoned Skill co
arXiv:2609.38426v1 Announce Type: cross Abstract: We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-L
arXiv:2609.38349v1 Announce Type: cross Abstract: Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long
arXiv:2609.38345v1 Announce Type: cross Abstract: Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically as
arXiv:2609.39727v1 Announce Type: new Abstract: Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet
arXiv:2609.38980v1 Announce Type: new Abstract: Radar hardware faults threaten automated perception, motivating accurate, compact diagnosis and understandable maintenance guidance. We introduce SCORE-
arXiv:2601.12310v2 Announce Type: replace Abstract: Self-training systems often degenerate due to the lack of an external criterion for judging data quality, leading to reward hacking and semantic dri
arXiv:2609.39466v1 Announce Type: new Abstract: In this work, we introduce a new clustering method, namely T-ARC (Topology-Aware Randomized Clustering), that corrects the geometric bias of K-means by
arXiv:2609.38205v1 Announce Type: new Abstract: System prompts are the primary lever practitioners use to control language model behavior, yet what they actually do to the computation inside the trans
arXiv:2609.38817v1 Announce Type: new Abstract: Large reasoning models (LRMs) improve performance on complex tasks through extended reasoning, yet the same process can degenerate into redundant verifi
arXiv:2609.39325v1 Announce Type: new Abstract: The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents require
arXiv:2609.37721v1 Announce Type: cross Abstract: Robot policies increasingly incorporate semantic reasoning and future-world prediction, yet combining these capabilities does not guarantee that local
arXiv:2609.36770v1 Announce Type: new Abstract: Can a population of neural networks develop a useful division of labor without a shared gate or gradients between agents? We study a setting where each
arXiv:2609.37808v1 Announce Type: new Abstract: Protein optimization aims to discover high-fitness sequences under a limited experimental budget. Existing machine-learning methods use task-specific pr
arXiv:2609.35911v1 Announce Type: cross Abstract: Adapting large language model agents during deployment requires not only retaining past experience, but also turning new observations into timely guid
OpenAI launched Dots at DevDay. My thoughts. First, the good. Always-on is really really really what the market needed. It's why I find myself reaching for Instinct so often. I don’t have to think abo
arXiv:2609.36653v1 Announce Type: new Abstract: Recurrent reasoning models have attracted growing attention for scaling test-time computation, typically by iteratively refining latent states with shar
arXiv:2609.36798v1 Announce Type: cross Abstract: Omni-modal large language models (LLMs) are expected to answer a question using the modality it explicitly refers to. However, existing training parad
In September 2026, Anthropic unveiled a suite of new AI products—Claude Tag, Sonnet 5.5, Fable/Mythos 5.1—and infrastructure releases such as Opus 5.5 and a plugins portal, following a record 47 billi
arXiv:2609.31792v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models perform strongly on manipulation tasks, their responses to invalid task premises remain underexplored. Exist
arXiv:2609.35616v1 Announce Type: new Abstract: Interactive 3D head generation requires coordinated speaking and listening motion that responds to an evolving conversation. Existing generators use inc
arXiv:2609.34491v1 Announce Type: new Abstract: Small-molecule optimization integrates medicinal-chemistry reasoning and computational evidence through iterative, multi-objective decisions. When large
arXiv:2609.34309v1 Announce Type: new Abstract: Executable programs offer explicit control over how images and videos are constructed, but generating runnable code is only the beginning of visual crea
Sarah Perez / TechCrunch: OpenAI announces new features for Codex, including reusable cloud development environments, a refreshed Codex CLI, a new code review experience, and more — OpenAI introduced
arXiv:2609.32862v1 Announce Type: new Abstract: A foundation model should not act in isolation as an embodied agent. Yet, existing methods often optimize individual components of the agent stack, such
arXiv:2609.34707v1 Announce Type: new Abstract: Object navigation requires an embodied agent to find an object in an unseen environment under partial observability and a limited motion budget. Existin
arXiv:2609.32759v1 Announce Type: new Abstract: We introduce the Extender, a log-structured variant of the standard Transformer architecture. In a standard Transformer, each layer communicates with su
arXiv:2607.14571v2 Announce Type: replace Abstract: Model growth adds parameters to a trained checkpoint and continues training, aiming to increase capacity while reusing the existing model instead of
arXiv:2609.35416v1 Announce Type: new Abstract: Continuous video counting requires distinguishing new observations from new objects or completed events. We introduce StaMina (State Maintenance), which
arXiv:2609.30414v1 Announce Type: cross Abstract: Cognitive psychology has studied how people encode, use, and learn concepts that describe categories, and how they represent, recognize, and acquire c
arXiv:2609.30977v1 Announce Type: cross Abstract: Uniform discrete diffusion models (UDMs) commonly use explicit time conditioning, but we find that it can often be unnecessary in practice. In this pa