Knowledge catalogue
arXiv:2507.15833v3 Announce Type: replace-cross Abstract: Human vision is a highly active process driven by gaze, which directs attention to task-relevant regions through foveation, dramatically reduc
arXiv:2607.11937v1 Announce Type: new Abstract: Mirror Theory proposes that an intelligent system should be studied not only by what it represents, but by what coherent continuations it can sustain un
arXiv:2607.12429v1 Announce Type: new Abstract: Consistent cross-view understanding under extreme viewpoint changes is essential for spatial intelligence, as it enables models to recognize the same sc
Never too late for any company to get in on open models. Inkling is a MoE transformer with 975B (41B active). Native multimodal support. Context lengths: 64K and 256K. Will be testing and providing th
Two DGX Spark and a Connect-X7 cable give you about 250GB of usable memory for 7000 8000 USD. This allows using some interesting models at 4-bit. For what seemed like an eternity, the only serious mod
arXiv:2607.11896v1 Announce Type: cross Abstract: Forecasting particulate matter (PM10) requires both station-scale accuracy and continuous spatial fields, especially during severe dust storms. Chemic
arXiv:2607.12341v1 Announce Type: new Abstract: Text-to-SQL is increasingly deployed across trust boundaries between data providers and users. Such deployment must balance three competing requirements
arXiv:2607.11916v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) with evolutionary computation has emerged as a powerful paradigm for automated heuristic design in com
arXiv:2607.12245v1 Announce Type: new Abstract: Few-shot industrial defect detection remains difficult for standard supervised detectors, which achieve poor performance on boundary-dominated industria
arXiv:2607.12266v1 Announce Type: new Abstract: Mixed-precision quantization must decide which parts of a model to keep at higher precision. A common premise, shared by sensitivity-based methods such
arXiv:2607.11889v1 Announce Type: cross Abstract: Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromis
arXiv:2607.11890v1 Announce Type: cross Abstract: Open-ended surveys offer valuable insights, but they are notoriously difficult to analyze at scale. Building on previous work that employed traditiona
Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automations, writing lint rules to catch repeat
arXiv:2607.12370v1 Announce Type: new Abstract: This paper proposes StratMamba, a dual-stream Mamba-based temporal modeling architecture, to more efficiently capture long-horizon temporal dependencies
arXiv:2607.12042v1 Announce Type: new Abstract: Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation. Yet prevailing m
arXiv:2607.11898v1 Announce Type: new Abstract: Large-scale text corpora have become a quiet bottleneck in modern NLP, not just in storage, but in the accumulated cost of training, fine-tuning, and co
The best base model for training isn't about someone else's benchmarks. Excited to offer @thinkymachines' first open-weights model: Inkling. 975B MoE, multimodal, with Apache 2.0. A great foundation f
arXiv:2405.11667v2 Announce Type: replace Abstract: Local SGD is a popular optimization method in distributed learning, often outperforming other algorithms in practice, including mini-batch SGD. Desp
arXiv:2607.13031v1 Announce Type: cross Abstract: When one ball strikes another, then another, video models should predict the consequences of each bounce. In controlled experiments on multi-ball hard
Thinky with a ~1T param, 41B active, apache-2 model Benchmarks are a clear step up from Nemotron Ultra (55B active), new best American model, and omni input. A bit behind GLM 5.2 on agentic benchies,
arXiv:2607.12113v1 Announce Type: cross Abstract: One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around fi
arXiv:2607.11913v1 Announce Type: cross Abstract: Recent advancements in agentic AI have increasingly moved toward graph-based methods, driven by the demand for explainable, human-centered, and non-li
arXiv:2607.12946v1 Announce Type: cross Abstract: Recommender-system research for Vietnamese remains limited by the absence of a public, well-documented hotel interaction resource. Building such a res
arXiv:2607.11953v1 Announce Type: new Abstract: Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut? The question is usua
Bonsai 27B is a big step for local AI: 27B-class multimodal capability in a phone-class footprint. Congrats to @PrismML on the launch. Try Ternary Bonsai 27B on Together AI: https://www.together.ai/mo
For years, we’ve built with a clear priority: putting the practical needs of the enterprise first. Long before generative AI dominated the headlines, we were focused on building the global infrastruct
Highly-recommended overview of metacognition in LLMs. (bookmark it) Interesting behaviors in LLMs like confidence calibration, self-verification, knowing when to stop, and knowing what you do not know
Huge if true! We are talking about a 27B multimodal model that runs locally on a phone. That's wild! Bonsai 27B reaches up to 163 tok/s in 1-bit and 134 tok/s in Ternary on an NVIDIA GeForce RTX 5090.
ICYMI: @LangChain Deep Agents on @nvidia Nemotron 3 Ultra. frontier open-model agents at ~10x lower cost than closed. Run on Fireworks, then post-train it into specialized intelligence you own. https:
dam bois we eating good this week ngl, The velocity of the open_weight ecosystem right now is hitting a point where proprietary, closed-source APIs are losing their leverage on compute intelligence. W
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. What Anthropic’s latest AI discovery does—and doesn’t—show —Ja
Today, we’re announcing Bonsai 27B: the first 27B-class model to run on a phone. Bonsai 27B is the new multimodal flagship of the Bonsai family. Based on Qwen3.6 27B, it brings a new capability tier t
Ethan Mollick notes that image input represents the primary advanced capability of current AI models, and that tool‑use can effectively replace outputs from non‑omni models. He observes that multimoda
Absolutely fascinating work by @SakanaAILabs reproducing @kenneth0stanley Picbreeder in a non-interactive, VLM-agentic way. I've had years to reflect on Kenneth Stanley's ideas as originally communica
And then what is the point of Work? Just a dumbed-down version of Codex that secretly does coding but hides it? (I can understand, maybe, if the release was a 1st step towards something but there is n
arXiv:2607.08011v1 Announce Type: cross Abstract: Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these mode
arXiv:2607.08497v1 Announce Type: cross Abstract: Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, t
arXiv:2601.04920v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as coding partners, yet their role in accelerating scientific discovery remains underexplored. Th
arXiv:2601.10504v2 Announce Type: replace Abstract: As Large Language Models (LLMs) increasingly operate as Deep Research (DR) Agents capable of autonomous investigation and information synthesis, rel
arXiv:2607.08288v1 Announce Type: cross Abstract: In critical infrastructure, operational technology environments often cannot be actively scanned, and yet active system feedback is needed for risk as
arXiv:2607.07779v1 Announce Type: cross Abstract: Recent developments in AI for Mathematics (AI4Math), especially Large Language Model (LLM)-driven theorem provers, has achieved remarkable success in
arXiv:2607.07880v1 Announce Type: new Abstract: Synthesizing realistic full-body human interactions with articulated objects is a fundamental challenge for embodied AI and graphics, with applications
Perplexity has released two new AI models, GPT-5.6 Terra and Sol, which are now available for use in Perplexity's search platform and Perplexity Computer tool. These models represent updates to Perple
GROK 4.5 LEADS ON REAL PROFESSIONAL WORK BENCHMARK New data from Snorkel shows Grok 4.5 outperforming other frontier models on real-world professional tasks. On their GDPval+ benchmark (expert-created
arXiv:2607.08705v1 Announce Type: new Abstract: Rapid advancements in video diffusion models and temporal editing tools have enabled the generation of highly realistic human-centric videos, posing unp
arXiv:2607.07836v1 Announce Type: new Abstract: We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end
arXiv:2607.07740v1 Announce Type: cross Abstract: Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workfl
arXiv:2607.08080v1 Announce Type: new Abstract: Aspect Sentiment Triplet Extraction (ASTE) requires jointly identifying (aspect, opinion, sentiment) triples from a given review sentence. While large l
arXiv:2505.16456v3 Announce Type: replace Abstract: Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. Howeve
arXiv:2607.08269v1 Announce Type: new Abstract: Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML. We prese
arXiv:2510.19475v2 Announce Type: replace Abstract: Monocular 3D human pose estimation remains a fundamentally ill-posed inverse problem due to the inherent depth ambiguity in 2D-to-3D lifting. While
arXiv:2607.08147v1 Announce Type: cross Abstract: Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved th
arXiv:2607.08691v1 Announce Type: cross Abstract: Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conv
arXiv:2601.22588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this 'LLM-as-a-Judge' paradigm is costly, opaque,
arXiv:2204.06142v2 Announce Type: replace-cross Abstract: Institutions of higher learning, research institutes and other scientific research units have abundant scientific and technological resources
arXiv:2607.02300v2 Announce Type: replace Abstract: In the automotive domain, in-car scene understanding (ISU) enables the detection of safety-critical events, such as driver distraction, and supports
arXiv:2607.07748v1 Announce Type: new Abstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource
arXiv:2507.05240v2 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low
arXiv:2602.04718v2 Announce Type: replace-cross Abstract: A central premise in mechanistic interpretability is that meaningful concepts in language models are represented by linear features in activat
arXiv:2607.08400v1 Announce Type: cross Abstract: LLM agents reach users through resellers, who may rebrand a developer's agent or substitute a cheaper model. When provenance is disputed, attribution