Knowledge catalogue
arXiv:2604.08342v2 Announce Type: replace Abstract: Long context egocentric video understanding has recently attracted significant research attention, with augmented reality (AR) highlighted as one of
arXiv:2511.22226v2 Announce Type: replace Abstract: The standard theory of model-free reinforcement learning assumes that the environment dynamics are stationary and that agents are decoupled from the
arXiv:2510.12953v4 Announce Type: replace-cross Abstract: Recent medical vision-language models have shown promise on tasks such as VQA, report generation, and anomaly detection. However, most are ada
arXiv:2607.28658v1 Announce Type: cross Abstract: Federated pre-training offers a way to train foundation models on private or distributed data without centralizing the underlying datasets. However, e
arXiv:2607.29025v1 Announce Type: new Abstract: While recent image editing models have made rapid progress, multi-reference editing remains challenging, particularly in maintaining visual consistency
arXiv:2607.29058v1 Announce Type: new Abstract: Professional-document review is a constraint-checking problem in which decisions depend on relations among text, geometry, pages, and document revisions
arXiv:2607.29419v1 Announce Type: cross Abstract: In reinforcement learning, exploration with sparse and delayed rewards presents a significant challenge due to the limited feedback available for guid
fascinating comments on possible slowdown – but probably a red herring. - Anthropic and OpenAI presumably aren’t colluding to slowdown, they are asking governments to build a framework such that a slo
arXiv:2607.29596v1 Announce Type: cross Abstract: Vision-language-action models (VLAs), which leverage the cognition of multimodal information to infer physical-world actions, provide a generalized so
GPT-Live can listen while it speaks. To make that feel natural at ChatGPT scale, we rebuilt the voice stack from client to model. This new architecture keeps audio flowing continuously, so deeper reas
arXiv:2607.29600v1 Announce Type: new Abstract: Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has eme
arXiv:2607.29513v1 Announce Type: new Abstract: Generating safe corridors is essential for collision-free robotic motion planning, yet most existing methods rely on predefined reference paths, which b
Hey, Like a lot of people here, I use local models via Ollama on my desktop/server and wanted a mobile client that actually felt responsive, worked offline, and respected privacy. Most apps on the Pla
arXiv:2607.29274v1 Announce Type: cross Abstract: Claims that language models homogenise are usually measured against human judgements collected for the study, which makes the human side an artifact o
arXiv:2607.28638v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights. Viewed
arXiv:2607.28802v1 Announce Type: new Abstract: Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the
arXiv:2607.28679v1 Announce Type: new Abstract: Multi-agent planning problems arise in a variety of engineering applications, such as multi-robot wildfire fighting and unmanned aerial inspection in fa
arXiv:2607.28629v1 Announce Type: new Abstract: The rapid transition from reactive large language models (LLMs) to persistent, action-capable systems has exposed critical gaps in the architectural und
arXiv:2607.28982v1 Announce Type: cross Abstract: Recent language models achieve strong performance across a variety of tasks, but conventional adaptation applies updates uniformly across training sam
Part of the challenge with the AI math advances is the current air of secrecy around them. We don't know how Astra/Fable/Mythos etc are trained. We know many mathematicians have been paid to create tr
arXiv:2607.29008v1 Announce Type: cross Abstract: Modern opaque AI models prize performance over interpretability, which makes testing difficult. However, formal statistical tests conducted on a model
For too long, enterprises with legacy mainframe estates have been faced with a high-stakes dilemma: continue maintaining their mainframes, essentially kicking the modernization can down the road (they
arXiv:2607.28995v1 Announce Type: new Abstract: Accurate plant leaf modeling is fundamental to downstream tasks such as plant growth monitoring, and phenotyping for yield estimation. Autonomous roboti
arXiv:2607.29241v1 Announce Type: cross Abstract: Optimizing modern recommender models still depends heavily on engineers manually iterating over architectural, objective, and training-strategy change
arXiv:2607.29591v1 Announce Type: new Abstract: KV cache compression is essential for efficient long-context inference. Existing eviction methods permanently discard unselected tokens and consequently
arXiv:2607.17977v2 Announce Type: replace Abstract: We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and p
arXiv:2607.29209v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) sco
arXiv:2607.29679v1 Announce Type: new Abstract: We study empirical scaling properties for text conditioning in visual generation. Such properties have rarely been measured because diffusion loss does
Has anyone figured out how to enable speculative decoding with deepseek v4 flash 0731 on llamacpp? I’m on the right release for llamacpp (b10228 or earlier) and running am17an’s draft model with unslo
OpenAI has redesigned the ChatGPT Voice stack—from client to model—to enable continuous audio streaming, allowing GPT‑Live to listen while speaking without interruption. The new architecture supports
arXiv:2607.28643v1 Announce Type: cross Abstract: Automating facilitation in online discussions is a long-standing social concern given the increasing time we spend on online spaces and the failure of
arXiv:2607.29278v1 Announce Type: new Abstract: Existing cross-domain few-shot segmentation approaches suffer from high training costs due to source-domain episodic training and pixel-wise dense predi
Checkmate: you can’t take the harness (which is typically in large part symbolic) away from the neural model without giving up performance. HUGE victory for neurosymbolic AI, straight from @AnthropicA
Hello, Also I want to join the hype of posting token specs. CPU: 2x Intel Xeon CPU E5-2650 v4 @ 2.20GHz RAM: 2x 4 Channel 2400MHz DDR4 GPU: 1x AMD Radeon 7900 XTX 24GB 3x AMD Instinct MI60 32GB Strang
Nine iterations of BabyAGI in three years, and yet the bit that @yoheinakajima kept coming back to was graphs. @aiDotEngineer published where that landed, 'Active Graph Agent Runtime (BabyAGI 4)', on
Open letters about AI development I wrote this summary of the past few weeks of open letters as a section of my sponsors-only newsletter but I've decided to share it here as well. Open Weights and Ame
# Running DeepSeek-V4-Flash-0731 (155 GB MoE) on a DGX Spark with vLLM-Moet 2-bit quantization I used Deepseek-v4-Flash-0731 cloud API settig up vllm-moet to run deepseek-v4-flash with MTP locally on
This wins the prize for sleazy misrepresentation. @mattShumer took my 2023 argument for hybridizing LLMs with symbolic tools – which is *exactly* what everyone does nowadays – and made it sound like I
Top eight misconceptions about OpenAI’s amazing new Astra math results. 1. Expertise in one domain does not at all guarantee expertise in all or even most domains. There is an important, principled re
https://huggingface.co/tsfrm/vacuum-16t A 16.5-trillion-parameter model that contains nothing. This model is just a ████ you to the labs and companies who say that 'haha I have the biggest model out t
I know in in this community LLM's are generally used for coding but there are other usecases besides coding and those usecases should be tested too. I also know benchmarks can sometimes be benchmaxxed
2/ a cost benchmark showed the same coding task running three to four times cheaper, depending purely on the harness wrapped around the model. Same intelligence, wildly different accuracy and cost, de
Hello fellow local AI people! I took 'you must create your own benchmarks' literally, and built a website for this. How does the end result look like Let's say I want to know which model has most comm
An internal version of Astra, @OpenAI’s next major model family, solved 10 major open problems in mathematics, quantum complexity, and theoretical computer science. We believe it will be a major step
great write up, evals are hard! here are 2 broad buckets we use to evaluate agents: 1. Measure the State of the World 2. Agent as a Judge on the Trajectory 1. Measure the state of the environment befo
Some things to note: 1) AI is getting very good at math and science. 2) Two years ago LLMs could not do basic math consistently 3) According to @polynoamial this cost less than $2000 in current API co
“Stochastic parrots” is not my term (it’s @emilymbender’s). But a lot of people today commenting on it are confused. To some extent (though I don’t think it’s a perfect metaphor, and have said that be
Ten advances in mathematics and theoretical computer science A few days ago it was Anthropic discovering cryptographic weaknesses with Claude using Mythos Preview, spending 100,000 on tokens and with
The “AGI-is-near” community keeps committing the same logical fallacy over and over; I have seen it at least half a dozen times today alone. Every time there’s an advance, I see the same error. Here’s
Your design, your model. Create with your pick of the world's leading models, including Claude, GPT-5, Gemini, Kimi, and GLM. Compare outputs across model families and keep the result that nails it. O
arXiv:2607.26520v1 Announce Type: cross Abstract: Conversational AI agents commonly lack persistent memory across sessions. The obvious fixes like injecting full chat histories into the context window
arXiv:2607.27735v1 Announce Type: new Abstract: Speculative decoding alleviates the memory-bandwidth bottleneck in large language model inference, but its acceleration is jointly constrained by drafti
arXiv:2607.28625v1 Announce Type: new Abstract: Embodied intelligence faces a fundamental data bottleneck. Models must capture how first-person perception, whole-body motion, dexterous manipulation, o
arXiv:2607.28320v1 Announce Type: new Abstract: Monocular UAV videos provide valuable observations for dynamic reconstruction of complex urban scenes. However, such scenes exhibit pronounced spatiotem
arXiv:2607.27130v1 Announce Type: new Abstract: Ontology matching (OM) has traditionally been formulated as either equivalence discovery or subsumption matching. The existing OM systems identify only
arXiv:2607.27705v1 Announce Type: cross Abstract: Large language models can contribute useful ideas to mathematical research, yet long-horizon proof attempts remain difficult to coordinate, evaluate,
arXiv:2607.27600v1 Announce Type: new Abstract: Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years. Computationa
arXiv:2607.27512v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in multi-agent environments. However, the processes by which beliefs form and propagate among int
arXiv:2607.27851v1 Announce Type: new Abstract: Emotional dialogue research includes two influential strategy traditions. Empathetic dialogue prioritizes understanding a speaker's emotional experience
arXiv:2607.27269v1 Announce Type: new Abstract: Multi-head latent attention (MLA) is increasingly important for long-context LLM inference because compact latent states replace the growing key-value (