Knowledge catalogue
arXiv:2603.06140v2 Announce Type: replace-cross Abstract: Video object insertion is fundamental to video editing, yet existing diffusion methods often produce visually plausible but physically inconsi
arXiv:2608.05115v1 Announce Type: cross Abstract: Can computer vision help make classrooms safer? In this pilot study, we investigate privacy-aware and computationally efficient classroom incident rec
arXiv:2607.11844v2 Announce Type: replace Abstract: Recent Multimodal Large Language Models (MLLMs) achieve strong performance on single-view video understanding benchmarks. However, sports videos inv
arXiv:2608.03701v1 Announce Type: cross Abstract: World-action modeling has emerged as a promising paradigm for robotic control, as it empowers models to go beyond reacting to observations and anticip
arXiv:2608.04007v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning meth
arXiv:2608.00339v1 Announce Type: cross Abstract: AI agents increasingly perform open-ended tasks in settings where their conclusions can guide consequential decisions. We provide evidence that AI age
arXiv:2608.01875v1 Announce Type: cross Abstract: Most time series (TS) models are specialized for a single task, either understanding (i.e., returning text answers about a TS) or generation (i.e., re
Advanced reasoning and problem-solving, plus strong performance in Japanese language and Japan-specific context. Namazu is live on Merge Gateway now! https://x.com/SakanaAILabs/status/2084276852143919
OpenAI’s GPT‑Live can listen and speak simultaneously. The new voice stack routes audio through a dedicated fast path so that speech flows continuously while intensive reasoning and external tool call
Sakana Namazu: An LLM API with Japanese-vibes! 🎏 Built for Japanese enterprises, featuring frontier-level reasoning and built-in agentic tools. 開発者の皆様、大変お待たせしました！Sakana Chatのモデルが遂にAPIとして公開です。ぜひお試しください
We’re releasing the manuscripts, formal Lean certificates, and reasoning walkthroughs so mathematicians can examine these results and build on their ideas. https://openai.com/index/ten-advances-in-mat
arXiv:2607.27914v1 Announce Type: new Abstract: Multi-zone variable-air-volume control must balance thermal comfort, indoor air quality, and electricity use across several continuous actuators. Model
arXiv:2607.28449v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning tha
arXiv:2607.27145v1 Announce Type: new Abstract: As Multimodal Large Language Models (MLLMs) are increasingly deployed in decision-critical pipelines such as robotics, embodied AI, and safety monitorin
arXiv:2607.26432v1 Announce Type: new Abstract: Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but also attack semantics and image-grounded evidence f
arXiv:2607.26865v1 Announce Type: cross Abstract: LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, a
arXiv:2607.26977v1 Announce Type: new Abstract: Travel planning is a demanding stress test for tool-using LLM agents: a usable itinerary is a single artifact that must be right along many axes at once
A benchmark score reflects the model as well as the harness and settings used to run it. For long-running agents, retaining reasoning and compacting context lets the model build on what it has already
arXiv:2607.25554v1 Announce Type: new Abstract: Future event prediction carries broad social impact yet remains challenging. SOTA approaches augment LLMs with external agent frameworks whose predictiv
arXiv:2607.25961v1 Announce Type: cross Abstract: Ambivalence and hesitancy (A/H) are conflicting affective states that precede the delay or abandonment of health behaviour change. Recognition of A/H
arXiv:2512.06276v3 Announce Type: replace-cross Abstract: Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description. Exis
The problem: agent workflows alternate between GPU-heavy reasoning and GPU-idle waiting on tools. Run hundreds concurrently and their KV caches fight for memory. Engines evict on a dumb LRU policy, ev
Two of the people most responsible for scaling the transformer are now betting on a next act. @MillionInt ran the Reasoning 🍓 team at OpenAI. @_arohan_ was a pre-training lead on Gemini after years at
arXiv:2601.18350v5 Announce Type: replace-cross Abstract: Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interf
arXiv:2505.07889v4 Announce Type: replace Abstract: The realization of autonomous scientific experimentation is currently limited by LLMs' struggle to grasp the strict procedural logic and accuracy re
arXiv:2607.24471v1 Announce Type: new Abstract: A central question in the in-context learning literature is whether transformers can organize episode-level adaptation around different inductive-bias f
arXiv:2607.24424v1 Announce Type: new Abstract: Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features ca
arXiv:2607.23472v1 Announce Type: new Abstract: Modern video generation models can synthesize visually compelling and temporally coherent clips, yet controlling their physical behavior remains difficu
arXiv:2607.22385v1 Announce Type: cross Abstract: Diagnosing the root cause of anomalies is essential for safe industrial operation. Despite extensive sensor instrumentation, formulating hypotheses an
Long-horizon execution in Large Language Models (LLMs) remains unstable even when high-level strategies are provided. Evaluating on controlled algorithmic puzzles, we demonstrate that while decomposit
David Gewirtz / ZDNET: Opus 5 improves coding, reasoning efficiency, and prompt-cache-friendly tool use, and is priced at 5/1M input tokens and 25/1M output, same as Opus 4.8 — ZDNET's key takeaways —
arXiv:2607.20459v1 Announce Type: cross Abstract: Multi-hop question answering requires retrieving and integrating evidence from multiple contexts. Despite the rapid progress of current research, mult
arXiv:2607.21433v1 Announce Type: cross Abstract: Chain-of-thought reasoning models such as DeepSeek-R1-Distill-Qwen-7B exhibit a bimodal convergence pattern: generations either terminate within a tok
arXiv:2607.09328v2 Announce Type: replace-cross Abstract: Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across dis
arXiv:2607.19996v1 Announce Type: new Abstract: Machine Learning models are widely used for automating classification tasks by extracting statistical patterns from data. However, their performance det
arXiv:2607.19398v1 Announce Type: new Abstract: Multi-entity compositional questions pose significant challenges to existing retrieval-augmented language models. Conventional methods fall into a dilem
arXiv:2607.20064v1 Announce Type: new Abstract: Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents. This
arXiv:2607.13569v1 Announce Type: cross Abstract: Transit video understanding can provide valuable fine-grained data that conventional passenger counters and fare systems cannot capture. However, supe
arXiv:2607.13539v1 Announce Type: new Abstract: While traditional graphics methods often synthesize 3D indoor scenes autoregressively or hierarchically, recent vision-language model (VLM)-based genera
I demonstrated the incredible power of o1-preview/ reasoning less than two years ago by showing it could solve this crossword puzzle with only one hint. https://www.oneusefulthing.org/p/something-new-
arXiv:2607.08136v1 Announce Type: new Abstract: We present a general neurosymbolic reasoning and learning methodology based on a modular integration of answer set programming with an energy based mode
ChatGPT Work is powered by GPT-5.6. GPT-5.6 makes ChatGPT state of the art at reasoning through complex tasks and creating materials that match your templates, reference files, and preferred style. Ju
arXiv:2607.06625v1 Announce Type: cross Abstract: Process industries have accumulated validated specialist models, yet sensor drift, feedstock variation, and regime switching cause these models to deg
arXiv:2607.06327v1 Announce Type: cross Abstract: Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English. We p
For questions that require web search, deeper reasoning, or more complex work, GPT-Live can delegate to our latest frontier model behind the scenes, and brings the result back into the conversation wh
arXiv:2607.05511v1 Announce Type: new Abstract: Agentic video understanding equips models with long-term memory to autonomously process and respond to continuous, long-horizon multimodal streams. Howe
Massive open-source release! LingBot-Video isn't about video quality; it optimizes for physical reasoning, and it runs sparse: only 3B of 30B params are active at inference. MoE is finally showing up
arXiv:2607.02588v1 Announce Type: cross Abstract: Multimodal large language models excel on short clips but struggle on hour-long videos in an online setting, where frames are processed incrementally
arXiv:2601.11960v3 Announce Type: replace-cross Abstract: Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide w
arXiv:2607.02073v1 Announce Type: new Abstract: Long-context reasoning requires models to locate, revise, and synthesize evidence distributed across lengthy inputs. Existing long-context RL methods us
arXiv:2607.01237v1 Announce Type: cross Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high d
arXiv:2607.02436v1 Announce Type: cross Abstract: Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the as
we distilled 2.3M Claude Fable 5 reasoning traces into Qwen3-4B - 100% self-consistency @ 512 samples - 0.00 bits output entropy - zero hallucination variance turns out the student is not bounded by t
arXiv:2601.15588v2 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained fil
arXiv:2511.04694v5 Announce Type: replace-cross Abstract: As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instruction
arXiv:2606.31814v1 Announce Type: new Abstract: Lane topology reasoning aims to construct a lane graph from onboard sensor observations. Existing methods follow a detection and association paradigm th
arXiv:2606.31413v1 Announce Type: new Abstract: Composing independently trained LoRA adapters into a single large language model is useful for multi-domain adaptation, especially when the original tra
arXiv:2511.12309v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning. It consists of g
arXiv:2606.31157v1 Announce Type: new Abstract: Foundation models are increasingly integrated into embodied intelligence systems, but directly assigning them structured prediction tasks requires preci
arXiv:2606.30698v1 Announce Type: new Abstract: Robotic-assisted endovascular interventions demand accurate, stable, and context-aware guidewire navigation in complex and patient-specific vascular ana