Knowledge catalogue
Yohei Nakajima discusses his exploration of stateful agents and concludes that current implementations have not yet achieved what the concept truly entails, suggesting the field is still in early stag
I had early Gemini Omni access: 'sea otter in a pilot's uniform explains why Spirit Airlines went bankrupt to a river otter who is distracted by their laptop while they are in a hot air balloon over N
The search results focus on OpenCode + Ollama integration but don't specifically cover the AgentRouter tool. Let me provide a knowledge base entry based on what the title and context suggest: A tool d
I remember when people were saying 'It's useless to open-source big models because nobody will be able to run them fast'.... Cerebras is now running Kimi K2.6 – a trillion parameter model – in enterpr
arXiv:2605.16457v1 Announce Type: cross Abstract: Transformer-based world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-ho
arXiv:2605.16682v1 Announce Type: new Abstract: Identifying latent state representations and dynamics is essential when direct modeling in observation space is infeasible, particularly under partial a
arXiv:2603.17577v2 Announce Type: replace-cross Abstract: Can latent actions and environment dynamics be recovered from offline trajectories when actions are never observed? We study this question in
arXiv:2603.00607v2 Announce Type: replace-cross Abstract: Multi-subject image generation requires seamlessly harmonizing multiple reference identities within a coherent scene. However, existing method
Sam Altman posted a humorous tweet on X suggesting that if the tweet received 1 like, a person named Tibo would reset Codex rate limits, likely referencing internal OpenAI API management or a playful
arXiv:2605.16816v1 Announce Type: new Abstract: Human-robot collaboration (HRC) can benefit from robots' abilities to interpret human emotional states. However, current emotion recognition (ER) models
arXiv:2605.17248v1 Announce Type: new Abstract: Diffusion-based extit{image-to-video} (I2V) generation has become a central direction in generative models by turning a reference image, with optional c
arXiv:2605.17865v1 Announce Type: new Abstract: LiDARs are being increasingly deployed for consumer imaging in handheld, wearable, and robotic applications. These sensors can capture the time-of-fligh
arXiv:2605.17179v1 Announce Type: new Abstract: Emotion understanding is a fundamental challenge in affective computing and artificial intelligence. While existing approaches predominantly focus on fa
In this post, we show three ways to implement Programmatic tool calling (PTC) on Amazon Bedrock: a self-hosted Docker sandbox on ECS for maximum control, a managed solution using Amazon Bedrock AgentC
arXiv:2605.18500v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly leveraged tool invocation to enhance their reasoning capabilities. However, existing approaches typically
arXiv:2605.18324v1 Announce Type: cross Abstract: Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this paper, we systematically investigate several design
arXiv:2605.18561v1 Announce Type: cross Abstract: In retrieval-augmented coding, failures often begin when the relevant file is absent from the retrieved context. Under frozen generic tokenization, wh
arXiv:2509.18150v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is oft
arXiv:2505.06852v2 Announce Type: replace Abstract: Random forest regression is a powerful non-parametric method that adapts to local data characteristics through data-driven partitioning, making it e
arXiv:2605.18068v1 Announce Type: cross Abstract: Residual error propagation remains a fundamental problem in recurrent models, where small prediction inaccuracies compound over time and degrade long-
arXiv:2605.16665v1 Announce Type: new Abstract: Continental-scale knowledge of subsurface temperature is limited by the cost and sparsity of borehole measurements, but such information is essential fo
arXiv:2605.18601v1 Announce Type: new Abstract: Modern interactive video world models have achieved impressive visual fidelity, yet lack fine-grained multi-entity control and cross-entity, cross-world
arXiv:2603.20873v2 Announce Type: replace Abstract: Federated learning (FL) is a communication-efficient collaborative learning framework that enables model training across multiple agents with privat
arXiv:2509.07793v4 Announce Type: replace-cross Abstract: How should well-being be prioritised in society, and what trade-offs are people willing to make between fairness and personal well-being? We i
arXiv:2605.16390v1 Announce Type: new Abstract: We investigate whether the training protocol can induce spatial locality in the early layers of a Vision Transformer (ViT) trained from scratch, without
arXiv:2510.24680v2 Announce Type: replace Abstract: While imitation learning (IL) has enabled successful visual navigation in many common environments, IL policies are prone to unpredictable failures
arXiv:2601.16172v2 Announce Type: replace Abstract: RL-trained Lean theorem provers mode-collapse at inference time: on miniF2F-test with DeepSeek-Prover-V1.5-RL, doubling the i.i.d. sampling budget f
arXiv:2605.18337v1 Announce Type: new Abstract: Large-scale news corpora support a wide range of research in Computational Social Science and NLP, yet access remains constrained: commercial archives i
arXiv:2605.17930v1 Announce Type: new Abstract: While the approximation properties of single-layer Transformer architectures have been studied in recent works, a rigorous theoretical understanding of
arXiv:2602.18217v2 Announce Type: replace Abstract: Real-time sentence comprehension imposes a significant load on working memory, as comprehenders must maintain contextual information to anticipate f
arXiv:2605.16809v1 Announce Type: new Abstract: The quality of graph-structured data is fundamental to the success of modern graph analysis techniques such as Graph Neural Networks (GNNs). However, re
arXiv:2605.18467v1 Announce Type: new Abstract: Recent diffusion-based methods have achieved impressive progress in video content manipulation. However, they typically ignore the accompanying audio, l
arXiv:2605.17219v1 Announce Type: cross Abstract: Artificial Intelligence (AI) is widely adopted today for its ability to detect patterns, automate tasks, and reduce time and cost across various appli
arXiv:2605.18006v1 Announce Type: cross Abstract: Because LiDAR sensors acquire point clouds with a fixed angular resolution, the resulting data can be systematically parameterized and efficiently com
arXiv:2605.18024v1 Announce Type: cross Abstract: Cooperation is central to multi-agent reinforcement learning (MARL), yet learned coordination can be fragile when external perturbations disrupt inter
arXiv:2605.17829v1 Announce Type: new Abstract: AI evaluation is undergoing a structural change. Large language models (LLMs) are increasingly deployed as systems that act over time through tools, env
arXiv:2605.17774v1 Announce Type: new Abstract: Large language models are increasingly used as planning components in agentic systems, but current tool-use pipelines often require full tool schemas to
arXiv:2510.21523v2 Announce Type: replace Abstract: Sequential generative models conditioned on uncertain rewards are central to AI-driven scientific discovery, yet the epistemic uncertainty they inhe
Databricks introduced AI spend controls as part of its Unity AI Gateway, enabling organizations to monitor, manage, and optimize costs associated with AI model usage and API calls. The feature likely
This article announces a collaboration between Anthropic's Claude and Modal that enables Claude to operate as managed agents within Modal's sandboxed environments. The integration allows Claude to saf
OpenAI announced its expansion into Singapore, establishing a presence in the Asia-Pacific region to better serve local customers and developers. The announcement likely covers OpenAI's commitment to
Introducing OpenAI Guaranteed Capacity: a new offering that enables customers to guarantee long-term access to OpenAI compute. We’ve made long-term investments in infrastructure, partnerships, and cap
The Ettin Reranker Family represents a new suite of reranking models released on Hugging Face designed to improve retrieval-augmented generation (RAG) systems by reordering search results based on rel
arXiv:2305.07152v4 Announce Type: replace Abstract: Robotic assisted (RA) surgery promises to transform surgical intervention. Intuitive Surgical is committed to fostering these changes and the machin
arXiv:2505.09203v2 Announce Type: replace-cross Abstract: Developing inverse design methods for functional materials with specific properties is critical to advancing fields like renewable energy, cat
arXiv:2605.16528v1 Announce Type: cross Abstract: The latest improvements in artificial intelligence (AI) raise new challenges for intellectual property laws, particularly concerning the inventorship
arXiv:2605.16318v1 Announce Type: new Abstract: Building and maintaining state to learn policies and value functions is critical for deploying reinforcement learning (RL) agents in the real world. Rec
Google I/O 2026 is where Google shared how it's making AI more helpful for everyone, releasing new models including Gemini Omni and Gemini 3.5. The event showcased advancements to Google's agent-first
At I/O 2026, Google announced that AI is transitioning from something users actively open to a background service that completes tasks automatically. The company introduced Gemini Spark, a new agentic
arXiv:2605.18113v1 Announce Type: new Abstract: Prompt optimization has often been framed as a discrete search problem to find high-performing and robust instructions for an LLM. However, the search r
Iranian lawmakers have proposed charging tech companies like Google, Meta, and Microsoft annual fees for fiber-optic cables running beneath the Strait of Hormuz . The proposal includes requiring these
arXiv:2605.17799v1 Announce Type: new Abstract: Long-tailed out-of-distribution (LT-OOD) detection is often addressed with specialized training, including auxiliary out-of-distribution (OOD) data, abs
arXiv:2605.17268v1 Announce Type: new Abstract: We present the first systematic study of faithfulness in Vision-Language-Action (VLA) driving models, analyzing 300 Alpamayo-R1-10B inferences across 10
arXiv:2605.18320v1 Announce Type: cross Abstract: Offline reinforcement learning methods typically enforce strict constraints to ensure safety; yet this rigidity often prevents the discovery of optima
arXiv:2605.16708v1 Announce Type: new Abstract: Learning meaningful latent representations from nonlinear fMRI data remains a fundamental challenge in neuroimaging analysis. Traditional independent co
arXiv:2605.16571v1 Announce Type: cross Abstract: Time-to-event data is widespread across the life sciences and engineering, but it is typically encountered together with censoring, which complicates
Ethan Mollick discusses how a model's instruction-following capabilities and video processing abilities expand its potential applications and use cases. He emphasizes that combining strong instruction
arXiv:2605.17251v1 Announce Type: cross Abstract: Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setti
Its a reason why there may be increased demand for some jobs disrupted by AI: when your local midsized insurance broker wanted software, there was no way they could even consider building internally.
Gary Marcus critiques podcasters for avoiding balanced discussion of contentious issues that significantly impact society, suggesting there is an reluctance to present opposing viewpoints on important