Knowledge catalogue
For the last few months, I ran DeepSeek v4.0 flash (NVFP4). First 0731, then visionexp because it was a free improvement. I got around 65 tps decode and almost 2k prefill, and ran 4-5 agents in parall
Nonobench measures how well LLMs solve nonograms (picross). Each model gets the row and column clues once and returns the full grid. No tools, one attempt per puzzle. Method: - Standard mode: 30 puzzl
Auto-generated synthesis of 29846 entries about arxiv-cs-ai
Auto-generated synthesis of 3157 entries about techmeme
Not a bot. Not a Strata shill. Just sharing my experience. So, I have an R9700 in my machine, plus an RTX 5060 Ti, and 64GB DDR5 system RAM. Overall, not a bad setup. Anyway, I mainly run a daily driv
Banger paper from CMU on harness learning. (bookmark it) Also, pay attention to this important new AI engineering skill of improving agents by editing their harness code instead of their weights. Seei
Reupload: I'm adding this again, since previous post had a totally stupid title which made people assume this app is some kind of cloud/proprietary models UI - this is totally not the case here. In ve
There are quite often posts here complaining that Krea 2 is too predictable / different seeds give almost the same output / you need to type in extremely long prompts to get good images / there is no
That video is 2 years old. Two years later, we are still far from human-level AI. Sure, AI has superhuman performance in a number of tasks (particularly in mathematics and coding and answering questio
Hi guys, I am pretty happy to announce MegaCapybara. Purpose build engine for RTX5090 that is focused on Qwen3.8 27B (more will come later). GITHUB (Engine) HUGGINGFACE (weights) Why ? 1. It beats Nin
Yann LeCun's (@ylecun ) latest talk at ETH Zürich Scaling LLMs to reach AGI is 'impossible' A large language model is trained on about 30 trillion tokens, which is roughly 10^14 bytes of text and woul
arXiv:2610.00376v1 Announce Type: new Abstract: We evaluate Jev on ten dataset-defined application labels in CESNET-QUICEXT-25 using only the first ten packets' sizes, directions, and inter-packet tim
arXiv:2610.01618v1 Announce Type: new Abstract: Agent evaluations increasingly go beyond a single success rate, reporting metrics such as cost, consistency, and robustness. Yet they typically treat th
arXiv:2610.01813v1 Announce Type: new Abstract: Mitotic counting is an important component of tumour grading, diagnosis and prognostic assessment across several tumour types, but manual assessment is
arXiv:2610.00854v1 Announce Type: new Abstract: Frontier vision-language models (VLMs) combine scene estimation, interaction grounding, and executable actions. Understanding how these abilities suppor
arXiv:2610.00052v1 Announce Type: cross Abstract: We evaluate six language-model configurations on requests for six distinct random integers from 1-49. Across 1,200 attempted calls using four English
arXiv:2601.11354v2 Announce Type: replace Abstract: Recent LLM-for-Space systems address mission planning, scheduling, operations support, simulator control, and autonomy, but their evaluations use di
arXiv:2610.01896v1 Announce Type: cross Abstract: Asynchronous reinforcement learning (RL) improves the efficiency of large language model post-training but introduces stale rollouts generated by earl
arXiv:2610.01138v1 Announce Type: new Abstract: Concurrent actions in large language model (LLM) agent environments require arbitration even when each proposal is individually valid. We implement a ty
arXiv:2610.00663v1 Announce Type: new Abstract: Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacker-specified outputs under hidden triggers. Existing
arXiv:2610.00092v1 Announce Type: cross Abstract: Data agents over structured sources must fit database schema into the model's context window. Large catalogs can span many databases and thousands of
arXiv:2610.01054v1 Announce Type: cross Abstract: In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requir
arXiv:2610.00238v1 Announce Type: cross Abstract: Long-term memory agents increasingly rely on it- erative search and reusable experience to answer questions over large personal, factual, or narrative
arXiv:2610.00418v1 Announce Type: new Abstract: Scaling Transformers to long contexts is constrained by the quadratic cost of self-attention and the linear growth of key-value cache memory transfer. S
arXiv:2610.00239v1 Announce Type: new Abstract: Model failover restores availability, but changes which financial institutions share decision errors. We formulate outage-contingent routing through a l
arXiv:2610.01794v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models rely strongly on language for describing task information, despite having multimodal inputs. We hypothesize that oth
arXiv:2610.01168v1 Announce Type: cross Abstract: Time Series Anomaly Detection has received increasing attention, driven by the growing availability of complex time series data. This surge has led to
arXiv:2610.01955v1 Announce Type: new Abstract: Outcome-based reinforcement learning can train language models to forecast real-world events, but prior forecasting work either freezes research context
arXiv:2601.22153v2 Announce Type: replace-cross Abstract: Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models. Although recent VLAs generalize well in static
arXiv:2610.01092v1 Announce Type: new Abstract: Video generation models are increasingly being explored as world simulators for embodied planning and learning. To do so effectively, these models must
arXiv:2508.16748v2 Announce Type: replace-cross Abstract: Prevalent multimodal self-supervised learning (SSL) methods rely on the redundancy assumption: that different views share substantial task-rel
arXiv:2610.01262v1 Announce Type: new Abstract: Timely and specific feedback is one of the strongest influences on student learning, yet it is difficult to sustain in large electrical engineering clas
arXiv:2610.02140v1 Announce Type: cross Abstract: Introducing new capabilities to frontier models has long been the goal of posttraining, which predominantly employs supervised finetuning (SFT) and re
arXiv:2610.01192v1 Announce Type: new Abstract: Streaming vision-language models must process continuously growing video streams under a bounded compute budget, creating a persistent tension between r
arXiv:2610.02058v1 Announce Type: new Abstract: Despite the success of Time Series Foundation Models (TSFMs) on broad benchmarks, their ability to internalize basic temporal logic, especially in setti
arXiv:2610.01014v1 Announce Type: new Abstract: Voting over multiple LLM responses is a common primitive in test-time scaling and ensemble inference. Collecting more responses can expand the candidate
arXiv:2610.01382v1 Announce Type: new Abstract: We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability. Across open-en
arXiv:2610.00576v1 Announce Type: new Abstract: In this paper, we propose Gestalt, a new paradigm of large multimodal model built around multimodal interplay. Despite rapid advances, large multimodal
arXiv:2610.00984v1 Announce Type: new Abstract: Accurate medication recommendation is central to clinical decision-making, directly determining therapeutic efficacy and patient safety. However, existi
arXiv:2505.12269v4 Announce Type: replace-cross Abstract: We examine how the cost of transforming qualitative information into precise numerical estimates--a form of integration cost--creates a struct
arXiv:2610.00623v1 Announce Type: new Abstract: Speculative decoding has achieved substantial lossless speedups for LLMs, but remains less effective for large vision-language models (LVLMs), where lig
arXiv:2610.01110v1 Announce Type: new Abstract: How much can test-time computation improve a language model, and at what cost? Test-time scaling is widely proposed as a substitute for larger models, b
Hey local AI community, I've been working on this for a while and finally feel ok sharing it. It's a cyber benchmark where the model gets a shell in an isolated docker box and has to find the exact fl
💯💯💯: “If AI is going to produce trustworthy and genuinely novel insights in science, medicine and beyond, we need systems whose conclusions arise from an auditable process of evidence, inference and b
arXiv:2610.00648v1 Announce Type: new Abstract: AI coding agents are ubiquitous in engineering workflows amongst industry and academia. Yet, despite their use in app coding, relatively less attention
arXiv:2610.02196v1 Announce Type: cross Abstract: We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills,
arXiv:2602.20294v2 Announce Type: replace-cross Abstract: Simulating real personalities with large language models requires grounding generation in authentic personal data. Existing evaluation approac
arXiv:2610.01201v1 Announce Type: new Abstract: Object permanence, keeping track of an object's identity and position while it is occluded, is central to video representations that track, predict and
arXiv:2610.01652v1 Announce Type: cross Abstract: Structured policies improve efficiency, robustness, and interpretability in imitation learning by introducing task-specific inductive bias, but existi
arXiv:2510.15125v3 Announce Type: replace-cross Abstract: Social media platforms play a pivotal role in shaping political discourse, but the scale and rapid evolution of online content make systematic
it’s honestly insane how much of the modern tech tree has been unlocked because of a single guy thanks to Elon we have - online payments - mass market electric cars - batteries and grid-scale energy s
Looking for some ideas from people who know a lot more about this than I do. We've got funding for a small AI lab in a public further education college in Ireland (roughly community college in the US)
arXiv:2610.01064v1 Announce Type: cross Abstract: Retrieving the right tables is a prerequisite for Text-to-SQL over realistic databases. Dense table retrievers rank schema elements independently, but
arXiv:2603.16065v3 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has shown strong potential for improving robotic manipulation policies, yet its practical use remains bottlenecked
arXiv:2610.01393v1 Announce Type: cross Abstract: Constructing typed, justified semantic links between ontologies is essential for enabling interoperability across heterogeneous and interdisciplinary
arXiv:2610.01153v1 Announce Type: cross Abstract: Looped Transformers introduce recurrent depth as a new scaling axis for LLMs: by repeatedly applying shared Transformer blocks, they increase effectiv
arXiv:2610.01118v1 Announce Type: cross Abstract: A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what t
arXiv:2610.00888v1 Announce Type: cross Abstract: Multi-token prediction (MTP) improves the throughput of autoregressive generation by enabling the language model to draft multiple next tokens per for
arXiv:2610.00430v1 Announce Type: cross Abstract: Autonomous large language model (LLM) agents increasingly interact in network environments where adversarial content can propagate between agents. Kno
arXiv:2505.17613v2 Announce Type: replace Abstract: Automatically evaluating multimodal generation presents a significant challenge, as automated metrics often struggle to align with human evaluation,