Knowledge catalogue
arXiv:2608.18361v1 Announce Type: new Abstract: Figurative language is deeply culturally embedded; fluent use requires not just linguistic competence but cultural immersion. We ask whether LLMs can le
arXiv:2602.02060v2 Announce Type: replace-cross Abstract: Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains unclear whether their predictions can be contro
Finally a good paper testing whether agents can really post-train other agents. (bookmark it) They analyzed a large corpus of publicly released post-training trajectories. Across tasks, the agent lock
Hey LocalLlama, Henry from Cactus here! When we trained Needle 2, I had a strict rule to not expose the model to any data sample that remotely felt like these benchmarks. It seemed over-the-top, but b
arXiv:2608.19174v1 Announce Type: cross Abstract: This technical report describes our winning submission to the AES AIMLA 2025 Challenge on querying sound effects by vocal imitation. We investigate tw
arXiv:2608.18534v1 Announce Type: new Abstract: Large language models are increasingly used to support financial operations, but their apparent reasoning performance can depend on whether they receive
arXiv:2608.18099v1 Announce Type: new Abstract: Investment management is a high-stakes domain in which agentic AI systems must do more than generate plausible text. They must retrieve point-in-time da
arXiv:2606.22361v2 Announce Type: replace-cross Abstract: Why do multilingual language models sometimes generate in the wrong language, and why is this so hard to fix? We introduce Language Identity H
arXiv:2608.18656v1 Announce Type: new Abstract: Inference with transformer models on CPUs is increasingly important, especially for Small Language Models (SLMs), where vector architectures are emergin
arXiv:2608.18423v1 Announce Type: new Abstract: Language model agents now execute bounded tasks reliably. Whether they can sustain effective decision-making over long horizons, where actions have cumu
arXiv:2608.18993v1 Announce Type: new Abstract: Electronic travel aids are pivotal for the independent mobility of the visually impaired. While Vision-Language Models (VLMs) offer rich environmental u
arXiv:2608.18136v1 Announce Type: new Abstract: Conversational agents now act for end users through tools while holding access to customer databases and internal policy documents that a caller can rea
arXiv:2608.18097v1 Announce Type: new Abstract: We present FrenchNews-7, a cross-publisher France-based French-language news editorial desk classification benchmark combining a large multi-outlet corp
I see https://github.com/linuxid10t/llama.cpp/tree/feature/g9v3-support but yeah... Considering that some results place it above Qwen 3.6 27B (the top performer until a few days ago) and that it is an
A majority of users in this sub use LLMs for coding/agentic tasks and I see why a lot of value is put into them but many try to say 'Well coding has improved therefore it can just use tool calling and
GLM-5.3 (Max) by @Zai_org has shifted the Pareto frontier for Code Arena: WebDev! GLM-5.3 (Max) would sit at #2 among open models (upon open weights release, and #8 overall) with 1597 pts in the Code
Howdy once again, I had a request to try out 5.3 on the benchmarks - they're unsaturated so it's a fun test right now! This one was interesting because I accidentally ran it on all 36 problems (rip 20
We are thrilled to announce that Google has been recognized as a Leader for the third year in a row in the 2026 Gartner® Magic Quadrant™ for Cloud-Native Application Platforms (CNAP). We believe this
arXiv:2608.18324v1 Announce Type: new Abstract: Machine-verifiable workflows produce governance records linking a task contract, model attempt, verifier decision, accepted output, and target origin. W
arXiv:2608.19009v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof ass
Great UI starts with good code. Give Qwen3.8-Max a try on Kilo! 👀 @kilocode Qwen3.8-Max landed #4 on Arena's Frontend Code leaderboard — one spot above Claude Fable 5. We ran both on the same 10 UI de
arXiv:2608.18752v1 Announce Type: cross Abstract: Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek. We introduce GreekBarRetrieval,
Grok 4.6 Grok 4.6 just tied for #1 on the Artificial Analysis Agentic Index • Grok 4.6 (high) — 59 • Claude Opus 5 (max) — 59 Outperforming Claude Fable 5 and GPT-5.6 Sol We’re entering the agentic er
arXiv:2608.19140v1 Announce Type: new Abstract: Frontier language models are compared, marketed, and benchmarked on capability -- what their best or average output can achieve. I argue this measures t
arXiv:2608.19066v1 Announce Type: cross Abstract: This paper proposes a lightweight, plug-and-play framework that improves robustness to viewpoint shifts in Vision-Language-Action (VLA) policies witho
I run local models on a 128GB Strix Halo and restart llama.cpp fairly often while testing builds, backends and model parameters. The annoying part is long-running agent sessions. Hermes/OpenCode sessi
arXiv:2608.18155v1 Announce Type: cross Abstract: Quantum machine learning (QML) for network intrusion detection (NIDS) is routinely reported to reach near-perfect accuracy, yet the most rigorous stud
arXiv:2606.20151v2 Announce Type: replace-cross Abstract: This work proposes a hybrid ANN-SNN pipeline that effectively leverages the rich embeddings of pretrained artificial neural networks (ANNs) to
I've been building AgentGraph Studio, a visual editor for designing multi-agent workflows and exporting them as runnable Python code. One thing I wanted to verify was whether the generated code actual
I pre-trained a 1.02-billion-parameter on Kimi K3 replica trained on 5.00 billion decontaminated tokens for $250. This model has 1.02 billion parameters, of which 145 million are active per token. It
I know so many first-time entrepreneurs building on Replit who simply don’t have the funds to spend heavily on usage, but are working on great projects. I’ve been fortunate enough to be able to spend
Four days ago I released a hyper-optimized Qwen3.8-27B inference engine for an RTX 3090 (82 tps single request, 672 peak). Since then it went to ~114, then ~138 tps single-user with DFlash2 drafting a
arXiv:2608.18696v1 Announce Type: cross Abstract: Digitizing the text from handwritten historical manuscripts is required to make them easily accessible, preservable, and to enable historical scholars
arXiv:2608.19026v1 Announce Type: new Abstract: Released in 2025, Institutional Books: Harvard Library (IB-HL) is a collection of 983,004 volumes (242B o200k_base tokens), originally digitized through
arXiv:2608.18972v1 Announce Type: new Abstract: Historical newspapers are an abundant record of public life, but their dense, irregular and sometimes noisy layouts make computational access to these m
Amazon Bedrock now offers OpenAI GPT-5.6 models (Sol, Terra, and Luna) in more than 25 AWS Regions with cross-Region inference. Learn how US geographic and global inference profiles route requests for
arXiv:2608.19006v1 Announce Type: new Abstract: Hate speech is a real and timely threat that affects a large portion of online users, especially youth and minority groups. While building reliable and
I have a big database of local court decisions with a legal sentence which is like a paragraph summary of the doc. I've been tinkering with FTing for many days now, all results inconclusive never beat
After Grok Build was caught uploading entire Git repos, we read the privacy docs for Claude Code, Codex, Cursor, GitHub Copilot, and Grok Build to compare what code leaves your machine, what gets reta
arXiv:2511.04707v2 Announce Type: replace-cross Abstract: Recent advances in long-context language models (LMs) have enabled million-token inputs, expanding their capabilities across complex tasks lik
arXiv:2608.18412v1 Announce Type: new Abstract: Effective sign language (SL) acquisition is crucial for deaf children, yet 95% are born to hearing parents who often lack proficiency in SL. SL recognit
Kimi K3 is now rolled out to over half of the subscription base for included usage, and we're continuing to expand access today. US and Europe-hosted and zero data retention. .@Kimi_Moonshot Kimi K3 i
arXiv:2608.18618v1 Announce Type: new Abstract: Autonomous laboratories hold great promise for accelerating scientific discovery. To achieve this vision, robots are supposed to dexterously manipulate
arXiv:2601.01684v2 Announce Type: replace-cross Abstract: While dense retrieval models have been the standard for state-of-the-art information retrieval, their deployment is often constrained by high
arXiv:2608.18089v1 Announce Type: cross Abstract: Instruction-tuned models often refuse harmful requests in English but comply with the same requests in Yoruba, Igbo, Igala, and Hausa. This suggests t
AntLing has released the full six-checkpoint matrix for the Ling-3.0 base model. tiny: pretrained, mid-trained, WSM-merged flash: pretrained, mid-trained, WSM-merged The concrete artifact is six separ
Just got the setup dialed in yesterday. Getting really good results and is making 3.8 usage feel faster in hermes. I got Qwen to specifically use Ling tiny for simple tasks like context compression an
arXiv:2608.18082v1 Announce Type: new Abstract: Although context windows have expanded significantly in recent years, hallucinations in long-context summarization remain a challenge. Long novels are b
arXiv:2608.18919v1 Announce Type: new Abstract: Tabular machine learning benchmarks typically summarize performance by averaging scores, ranks, or pairwise wins across datasets. Such aggregates are us
arXiv:2608.18341v1 Announce Type: cross Abstract: Persistent acoustic monitoring can detect machine faults without physical contact, but always-on inference is constrained by power, latency, and deplo
arXiv:2608.18096v1 Announce Type: new Abstract: Assessing whether multimodal content aligns with macro-societal values, such as peace, justice, and freedom, has become an increasingly urgent challenge
Replit announced the launch of its Free Mode on August 20, 2026, powered by OpenAI’s GPT‑5.6 “Luna” model. The announcement highlights increased productivity (“maximize making”) while reducing cost fo
arXiv:2608.18336v1 Announce Type: new Abstract: When evaluating language models on human exams, benchmarks typically score each response as right or wrong and report the overall accuracy. This approac
arXiv:2608.18419v1 Announce Type: cross Abstract: Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling capabilities and show promise in time-series predic
arXiv:2608.18937v1 Announce Type: cross Abstract: Recent Multimodal Large Language Models (MLLMs) are rapidly evolving into unified understanding and generation (UAG) frameworks. However, extending th
arXiv:2608.18704v1 Announce Type: cross Abstract: Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on
arXiv:2608.18744v1 Announce Type: new Abstract: Agents improve quickly against a reliable automatic metric and stall without one, and the applications that need them most, report generation among them
arXiv:2606.17809v2 Announce Type: replace Abstract: Automated pollen identification from microscopy remains a bottleneck in aerobiology, palaeoecology and biodiversity monitoring, because scalable sys
arXiv:2608.19000v1 Announce Type: new Abstract: Automating graphic design synthesis from user-provided elements requires both a coherent overall composition and the exact preservation of each asset. E
arXiv:2608.18489v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) and knowledge-graph-based retrieval-augmented generation (KG-RAG) aim to ground answers in explicit graph evid