Knowledge catalogue
arXiv:2608.02353v1 Announce Type: new Abstract: Recent advances in agentic workflow optimization automate workflow design through task-specific workflow search or input-conditioned architecture select
It is one of the best local models ever released, in both 20B and 120B versions. I always come back to it, especially the 120B version. Its only competition is, in my opinion, Qwen 3.5 122B, but that
arXiv:2608.01528v1 Announce Type: new Abstract: Vector symbolic architectures (VSA) are widely used for reasoning in neuro-symbolic (NeSy) AI, yet high-dimensional codebooks often create severe memory
arXiv:2608.01633v1 Announce Type: new Abstract: Large language models (LLMs) enable neural architecture search (NAS) directly over executable neural network programs. However, code-level flexibility d
arXiv:2608.00600v1 Announce Type: new Abstract: Standard multifingered grasp execution architectures plan a collision-free trajectory to a selected grasp pose and track it with a feedback law. Executi
arXiv:2608.02497v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models excel in robotic manipulation but suffer catastrophic performance drops when canonical instructions are simply parap
arXiv:2608.02470v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed as reasoning agents in real-world visual assessment pipelines, yet their spatial grounding remai
arXiv:2608.01988v1 Announce Type: new Abstract: Rapid advances in image generation models call for interpretable AI-generated image detection methods that not only determine authenticity but also prov
arXiv:2608.00518v1 Announce Type: new Abstract: 3D visual grounding aims to localize the target object in a 3D scene from a natural language query, requiring both fine-grained semantic understanding a
arXiv:2608.02343v1 Announce Type: cross Abstract: Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constra
arXiv:2608.02252v1 Announce Type: new Abstract: Recent vision-language models for chest X-ray understanding are largely built on image-report alignment and therefore rely heavily on MIMIC-CXR as the d
arXiv:2608.01918v1 Announce Type: cross Abstract: Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable
arXiv:2608.01356v1 Announce Type: new Abstract: Pathology foundation models (PFMs) provide strong tissue representations and have become central to digital pathology. However, deployment in disease-sp
arXiv:2608.01597v1 Announce Type: new Abstract: Search-augmented LM agents are typically trained with a binary exact-match reward, which throws away most of what a failed trajectory tells us about why
arXiv:2608.01358v1 Announce Type: new Abstract: Search-augmented large language model agents are increasingly capable of solving knowledge-intensive tasks, but their behavior when a multi-hop question
arXiv:2606.14741v2 Announce Type: replace Abstract: We introduce HorusEye, Language as Dynamic Attention for Emergency Visual Analysis. Our investigation followed five stages. The first one is benchma
arXiv:2608.01454v1 Announce Type: cross Abstract: Provenance-based intrusion detection systems (PIDS) frequently report strong performance, but the conclusions drawn from these results can be highly s
arXiv:2608.02089v1 Announce Type: new Abstract: Large language models often show users a final response and a short reasoning summary while the full reasoning trace stays hidden. We introduce an obser
arXiv:2608.00491v1 Announce Type: new Abstract: Graph self-supervised learning aims to learn transferable representations from large-scale unlabeled graph data. Joint-embedding predictive architecture
arXiv:2608.01193v1 Announce Type: cross Abstract: An AI development race creates a multi-agent safety dilemma. Each company can develop slowly and safely, or move faster while taking a risk that may r
arXiv:2607.11500v2 Announce Type: replace Abstract: Gaussian Splatting has emerged as an effective representation for video, but existing methods rely on per-video optimization. This leads to slow enc
arXiv:2608.00852v1 Announce Type: new Abstract: Understanding and controlling complex dynamical systems often requires executing thousands of numerical simulations across vast parametric landscapes, w
152 generations, deterministic grading (exact number/string/JSON/regex), no LLM judge on my 16GB laptop. task type | deepseek-r1:1.5b (1.1GB) | llama3.2:3b (2.0GB) | gemma:2b | codellama 7b arithmetic
Disclosure: I’m the author and maintainer of QuarkStar. I built QuarkStar, a small native inference engine inspired by Antirez’s DwarfStar. QuarkStar currently supports: Qwen3.6-35B-A3B, using the sam
If you missed today's K3 on Fireworks webinar, we've got you covered. We'll be partnering with @arizeai to chat more models on Thursday, August 6th. Sign up below! Next session, August 6 we'll be co l
arXiv:2608.01794v1 Announce Type: cross Abstract: Universal Multimodal Embeddings (UMEs) aim to unify various modalities and tasks into a shared representation space. In recent years, this field has w
arXiv:2608.00490v1 Announce Type: new Abstract: Can image-editing models discover visual rules in image space and complete problem-solving end-to-end? We tackle this question in the spirit of a human
The Ling-3.0-flash MoE is now open-weighted at 124B A5B params. I know the original announcements were before the Kimi K3, DeepSeek-V4-Flash and Qwen3.8 hype, but this model might still have a good ni
Went public in the last few minutes, both repos ungated. Ling-3.0-flash, BF16, 24 shards, ~255GB Ling-3.0-flash-fp8, official FP8, ~128GB 127.5B total, they quote 5.1B active. What jumped out at me in
arXiv:2608.01157v1 Announce Type: new Abstract: Large language models have made text the default medium for human--AI interaction, buttext alone cannot express the full range of responses required by
arXiv:2608.00956v1 Announce Type: new Abstract: This paper presents an interpretable machine-learning framework for predicting the splitting strength (ST) of asphalt concrete and supporting data-drive
arXiv:2608.01180v1 Announce Type: new Abstract: Traffic congestion prediction is essential for congestion mitigation, but the COVID-19 pandemic and related control measures altered travel behavior and
As part of the Agentic Data Cloud launch at Google Cloud Next ‘26, we announced two AI-powered database agents to simplify database management. These include the Database Onboarding Agent for Day 0 op
Mistral AI introduced Shieldstral, a 3‑billion‑parameter, open‑weights model designed for content‑safety tasks and capable of on‑device deployment. The announcement was shared via a tweet from @Mistra
Some of you may be aware that a few weeks ago, LM Studio announced a new agent, Bionic. This is pretty much an agentic harness for both local models and paid cloud models. But most aren't aware that L
arXiv:2608.02468v1 Announce Type: new Abstract: Interactive segmentation reduces the prohibitive cost of pixel-level annotation by allowing users to delineate objects with a few clicks. However, apply
arXiv:2608.01207v1 Announce Type: new Abstract: Test-time scaling lifts large language model reasoning by sampling many candidate solutions and selecting among them, yet the same recipe transfers poor
arXiv:2607.14990v2 Announce Type: replace Abstract: Neural radiance fields and 3D Gaussian Splatting assume that each training image is a sharp and geometrically consistent observation of the scene. M
June.ai Technologies Inc., a startup that uses artificial intelligence to modernize enterprise software environments, launched today with 20 million in funding. The pre-seed round was led by Time Vent
arXiv:2608.00860v1 Announce Type: new Abstract: The cost of storing and transmitting a trained neural network scales with its parameter count, a bottleneck for over-the-air updates, on-device librarie
Kimi K3 full model running on 16x GB10 cluster at 20+tps average (llama-benchy coherent corpus) 38tps peak, 750tps prefill. This is the first run of full k3 with dspark on my cluster. I will be doing
arXiv:2602.10441v2 Announce Type: replace Abstract: Data lakes have become a fundamental platform for large-scale machine learning by enabling flexible management of heterogeneous data. Despite their
arXiv:2604.03532v2 Announce Type: replace Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Repres
arXiv:2602.18662v2 Announce Type: replace Abstract: Causal discovery for both cross-sectional and temporal data has traditionally followed a dataset-specific paradigm, where a new model is fitted for
arXiv:2608.00569v1 Announce Type: new Abstract: Deploying billion-parameter Vision-Language-Action (VLA) policies on mobile robots creates a systems conflict: semantic reasoning benefits from cloud GP
arXiv:2608.00237v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs
arXiv:2608.00106v1 Announce Type: new Abstract: Agentic systems must decide not only what answer to produce, but which reasoning and execution operations should precede it. A controller may answer dir
arXiv:2608.01672v1 Announce Type: new Abstract: Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later. Test
arXiv:2608.01094v1 Announce Type: new Abstract: Federated learning enables medical-imaging models to be trained across hospitals, and privacy law, most explicitly the GDPR ``right to be forgotten'', t
LexisNexis Legal & Professional, a division of RELX plc, today announced the opening of its Customer Innovation Lab in New York City, which will deliver a new model for how legal artificial intelligen
Released today, with emphasis on agentic capabilities. I really like their models for simple, high volume tasks ('summarize these gazillion documents') and their 8b-a1b was my go-to for certain tasks
arXiv:2602.04789v4 Announce Type: replace Abstract: Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention rema
arXiv:2608.01614v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face a critical computational bottleneck when processing high-resolution imagery due to the O(N^2) memory complexity of So
Live and ready to build. Thanks for having us! @OpenRouter. Open weights dropping soon.⚡️ Qwen3.8 Max by @Alibaba_Qwen is live on OpenRouter. The new flagship has 2.4T parameters (95B active) and is b
arXiv:2608.02515v1 Announce Type: new Abstract: Long-running assistants and agents consume interaction streams that eventually outgrow the context. Existing context retention, summarization, and retri
Llama.cpp currently uses cpu based sampling for user with mtp enabled. The PR moves sampling to the gpu, which on a 5090 boasts an 8% increase in tok/s for qwen3.6:35b. I tested it on my P40 and obser
Release: llm-anthropic 0.26 Includes new features enabled by LLM 0.32: New models: claude-fable-5, claude-sonnet-5, and claude-opus-5. #75, #76 Added server-side tools for WebSearch, WebFetch, CodeExe
arXiv:2608.02404v1 Announce Type: new Abstract: The Loggia dei Lanzi in the Piazza della Signoria is one of Florence's most prominent structures visited by millions every year. Its construction histor
arXiv:2608.01456v1 Announce Type: cross Abstract: Agents are increasingly expected to act not only as task executors, but also as decision-makers on behalf of human users. This shift requires agents t
arXiv:2608.01662v1 Announce Type: cross Abstract: DeepSeek Sparse Attention (DSA) enables efficient long-context modeling through its Lightning Indexer. However, practical deployment remains constrain