Knowledge catalogue
arXiv:2510.12346v2 Announce Type: replace Abstract: Recently, biped robot walking technology has been significantly developed, mainly in the context of a bland walking scheme. To emulate human walking
arXiv:2607.27066v1 Announce Type: new Abstract: Scientific figure assessment in peer review differs fundamentally from general image quality evaluation: a figure must be visually legible, faithfully s
arXiv:2606.13317v2 Announce Type: replace Abstract: Skill self-evolution methods for LLM agents aim to turn execution trajectories into reusable skill documents. However, current pipelines typically d
arXiv:2510.08543v2 Announce Type: replace-cross Abstract: As Video Large Language Models (VideoLLMs) are deployed globally, it is important to assess their ability to reason across cultural contexts.
arXiv:2607.27069v1 Announce Type: new Abstract: Closed yes/no spatial benchmarks can reward a correct answer even when the image adds little support beyond no-image contexts. Under a fixed forced-choi
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:2503.07303v3 Announce Type: replace Abstract: Texts, whether literary or historical, exhibit structural and stylistic patterns shaped by their purpose, authorship, and cultural context. Formulai
Welcome to our latest Gemini Enterprise Agent Platform deep dive, a practical walkthrough where we’ll teach you how to build real-world, production-ready agents starting from step 1. If you haven’t al
arXiv:2607.24758v1 Announce Type: new Abstract: Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations rather than typical d
Enterprises are discovering that a scalable intelligence layer built on knowledge graphs delivers the institutional context that turns generic AI models into reliable production systems. As companies
arXiv:2607.25507v1 Announce Type: new Abstract: Transformer language models are usually analyzed through vector geometry, yet ordered context and rotary position encoding introduce explicit phase stru
arXiv:2606.18902v2 Announce Type: replace Abstract: Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do
arXiv:2607.25413v1 Announce Type: new Abstract: Transaction propensity prediction in B2B e commerce presents unique challenges distinct from B2C contexts, primarily due to the heterogeneous procuremen
Everyone is talking about Kimi K3, but if you jump straight into the technical report, you’ll quickly realize it’s standing on years of research -- just like any breakthrough is! If you want to unders
// Unfolding Sub-Agents for Long-Horizon ML Engineering // Watch a single agent work a machine learning engineering task for six hours you see issues like context fills with stack traces, dead experim
arXiv:2607.24795v1 Announce Type: new Abstract: Older adults' independent mobility enables out-of-home participation, well-being and health, yet pedestrian navigation systems still optimize primarily
arXiv:2607.26037v1 Announce Type: new Abstract: We present Wonder, a general-purpose video world model for real-time, camera-controllable world exploration. Given an image or a conditional video, Wond
arXiv:2607.24625v1 Announce Type: cross Abstract: Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynam
arXiv:2607.22663v1 Announce Type: new Abstract: Block diffusion has emerged as the dominant paradigm for scaling discrete diffusion language models (dLLMs), because decoding text in fixed-size blocks
arXiv:2607.22948v1 Announce Type: cross Abstract: The ORBIT (Operations Responses and Business Intelligence Toolkit) project was initiated to assess agentic AI for the upcoming ESnet 7 initiative and
arXiv:2607.24312v1 Announce Type: new Abstract: Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency acro
Secure artificial intelligence infrastructure startup Dymium Inc. today introduced GhostAI, a gateway designed to apply security and governance policies across the models, data, context and tools used
The Model Context Protocol (MCP) published its 2026-07-28 specification, the largest revision since launch: MCP is now stateless, with a governed extensions system and hardened authorization. Learn wh
arXiv:2607.24273v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong potential in financial reasoning, but existing benchmarks often evaluate domain knowledge, numerical reas
arXiv:2607.23946v1 Announce Type: new Abstract: We introduce Joint Flow Matching (JFM), a training framework for continuous normalising flows over multiple variables. Standard flow matching transports
arXiv:2606.16586v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) remain unreliable on fine-grained visual perception, even when high-resolution inputs preserve the necessar
arXiv:2607.23511v1 Announce Type: new Abstract: End-to-end autonomous driving systems commonly follow a cascaded two-stage pipeline where a perception stage compresses multi-modal sensor inputs into a
arXiv:2607.22665v1 Announce Type: new Abstract: Machine unlearning is becoming increasingly critical in the context of data privacy regulations, particularly for recommendation systems that are direct
arXiv:2607.23631v1 Announce Type: new Abstract: Gigapixel Whole-Slide Images (WSIs) present a fundamental computational bottleneck for vision-language models (VLMs) due to extreme sequence lengths. Ex
arXiv:2606.18037v2 Announce Type: replace Abstract: Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, datab
arXiv:2607.24701v1 Announce Type: new Abstract: Missing modalities in RGBT tracking often lead to incomplete and unstable multimodal feature representations that greatly degrade the performance. Exist
arXiv:2607.24276v1 Announce Type: cross Abstract: Large language models (LLMs) process text through subword tokenizers rather than directly reading characters or words. Because these tokenizers are tr
It has only been two days since I move 100% from Qwen3.5-27B F16 to ThinkingCap-Qwen3.6-27B F16. Where I was getting tps in 30-40 range (depending on the size of the context), I am definitely getting
Following some recent commits in llama.cpp, preserve_thinking behavior for chat templates included in older DSV4 ggufs got broken. This makes the model pretty dumb in a coding agent context. Adding kw
arXiv:2607.23265v1 Announce Type: new Abstract: Existing Large Vision-Language Models (LVLMs) struggle with long-form video understanding due to the quadratic computational cost of visual tokens. Whil
arXiv:2607.23920v1 Announce Type: new Abstract: Emotional image editing requires more than applying affective filters or modifying predefined visual factors: an effective edit must identify what a par
arXiv:2607.21646v1 Announce Type: new Abstract: Ensuring safety in reinforcement learning under nonstationarity requires determining whether a learning system can safely adapt to forecasted environmen
arXiv:2603.06851v3 Announce Type: replace-cross Abstract: We study contextual bilateral trade under full feedback when, conditionally on the context, trader valuations have bounded density but infinit
arXiv:2607.22314v1 Announce Type: new Abstract: Multiple Sequence Alignments (MSAs) provide protein language models with explicit evolutionary context, but their large depth makes subsampling unavoida
arXiv:2607.22389v1 Announce Type: cross Abstract: With the rapid adoption of long-context large language models (LLMs), the continuously growing KV cache during decoding has become the critical memory
Kimi K3 is live on Fireworks. Day 0, inference and training. US-hosted, and zero data retention. This is the first frontier open model in the 3 trillion parameter class. It sports 1M context, native v
tldr; we are going to host K3 on A100s (yes, thats correct, we'll try to see if it holds up), H200s & B300s - expect results for A100s & H200s this week while we setup the B300 cluster this weekend &
arXiv:2607.21936v1 Announce Type: new Abstract: Historical documents act as invaluable knowledge archives but often suffer from illegibility due to physical deterioration and damage. While existing re
arXiv:2603.12572v5 Announce Type: replace Abstract: Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchm
arXiv:2607.21672v1 Announce Type: cross Abstract: Long source-code contexts consume many text tokens, motivating the proposal to render code as images for vision-language models. Recent work asks whet
Releasing the model weights and technical report of Kimi K3. Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window. New model architecture:
The performance of AI agents depends not only on the underlying models but also heavily on their “harness”—the surrounding architecture that supplies context, state management, action execution, and t
**Summary:** Kimi K3 is a publicly available 3‑trillion‑parameter language model now live on Fireworks, offering 1 million-token context windows with native vision and reasoning that rivals top closed
The LangChain podcast where @hwchase17 interviews agent builders is full of alpha. Recent one with @EnoReyes was the best one yet. Sharing my unstructured notes: Eno keeps bringing back some core conc
arXiv:2607.21840v1 Announce Type: new Abstract: Learning high-fidelity point-cloud features in the 3D space poses significant challenges, including permutation invariance, lack of local context, diffi
arXiv:2607.21887v1 Announce Type: cross Abstract: Foreign language anxiety (FLA) can be a major barrier to second language acquisition (SLA), especially in conversational contexts. With the proliferat
This part is spot on: > 'Overall, we found that we were over-constraining Claude Code...while these constraints were once needed to avoid worst case scenarios, we have since found we can delete many o
Great to see this out, proud of the team!!! @AMD Instella 16B MoE foundation model, fully open with checkpoint after each stage from pretraining, long-context, SFT, DPO and RL. Dataset detail, trainin
Just noticed this exists, 1M context MOE with 48B par seems just like what Ive been looking for - it runs pretty damn fast too compared to Qwen 3.6 35B. after some testing it seems capable of producin
arXiv:2607.20448v1 Announce Type: new Abstract: We introduce Domyn-Small, a 10-billion-parameter open-weight reasoning language model released under the MIT license. Domyn-Small is the product of an i
arXiv:2607.20531v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed over Model Context Protocol (MCP) servers, yet the benchmarks used to evaluate them score th
https://huggingface.co/swiss-ai/Apertus-v1.5-70B https://huggingface.co/swiss-ai/Apertus-v1.5-8B Apertus 1.5 is a family of 8B and 70B parameter language models designed to advance the state of multil
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:2607.20720v1 Announce Type: cross Abstract: Harnessing the potential of electroencephalography (EEG) for brain research is fundamentally limited by intrinsic noise and the diffuse projection of
arXiv:2511.12290v2 Announce Type: replace Abstract: Automatic summarization of legal judgments liberates law professionals from heavy cognitive burden due to the complexity of the language, context-se