Knowledge catalogue
How to get 100% consistent product ads from one seedance 2.0 generation all directed from one chat with the hashtag Comfy MCP. @hellorob didn't let the agent improvise a pipeline. He pointed it at his
This post discusses the conceptual distinction between training-scaling and inference-scaling in machine learning models, while acknowledging related frameworks or concepts (possibly referencing Sol,
arXiv:2607.08758v1 Announce Type: new Abstract: Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biol
Key to this strategy is deterrence, 'Mutually Assured Compute Destruction' which gets its own section. It doesn't mention the generalization Mutually Assured AI Malfunction (MAIM) from Schmidt, Wang,
arXiv:2603.12478v2 Announce Type: replace Abstract: Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is
arXiv:2506.15138v2 Announce Type: replace-cross Abstract: Tokenization directly affects the inference efficiency of large language models, since fragmented tokenization increases sequence length and g
M.G. Siegler / Spyglass: Like the Claude app it imitates, the new ChatGPT “Super App”, which merges Codex with ChatGPT, is a tangle of toggles and strange UI decisions — Even if it's ultimately the ri
arXiv:2607.08085v1 Announce Type: new Abstract: Multi-query vehicle ReID aims to leverage complementary information from diverse views for robust feature learning. However, current methods suffer from
arXiv:2607.08077v1 Announce Type: new Abstract: AI developers face a dual-use dilemma. An AI capability that helps one user cure a disease can help another synthesize one. This dilemma could be resolv
arXiv:2607.07907v1 Announce Type: cross Abstract: With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or
New research from Meta. (bookmark it) It's on how to fix agents that forget previously made decisions. It's well know that long-horizon agents keep forgetting decisions they already made. Meta researc
Nick Frost, likely a notable figure in AI or machine learning, discusses his work and insights in a full-length podcast available on YouTube. The podcast was shared by Cohere, an AI company, suggestin
arXiv:2607.08371v1 Announce Type: cross Abstract: Synthetic multi-speaker conversations are widely used to train conversational automatic speech recognition (ASR) systems, but it remains unclear which
OpenWiki general purpose memory is meant to be complementary to codex/claude code memory: it's proactive & ambient, meaning it'll automatically go out into your world (via connections like gmail, x, n
arXiv:2512.16558v3 Announce Type: replace Abstract: Clustering is a cornerstone of modern data analysis. Detecting clusters in exploratory data analyses (EDA) requires algorithms that make few assumpt
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:2607.08429v1 Announce Type: cross Abstract: Male infertility is a significant yet often underdiagnosed aspect of reproductive health, with semen analysis serving as the cornerstone of clinical e
arXiv:2607.08399v1 Announce Type: new Abstract: Large language models process prompts by propagating activations through dozens of layers before generating a response. We ask whether the task-relevant
arXiv:2607.08111v1 Announce Type: cross Abstract: Training target speaker extraction (TSE) models for real conversational mixtures remains challenging because large-scale training corpora and clean ta
arXiv:2202.13142v3 Announce Type: replace Abstract: A key challenge of real-world image super-resolution (SR) is to recover the missing details in low-resolution (LR) images with complex unknown degra
arXiv:2607.08716v1 Announce Type: new Abstract: In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As tra
arXiv:2607.08029v1 Announce Type: new Abstract: The emergence of vision language models with fewer than 3 billion parameters has accelerated the implementation of on-device multimodal intelligence. Ho
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:2607.07844v1 Announce Type: cross Abstract: While closed-loop motion planners trained on large-scale, object-level datasets, e.g., nuPlan, demonstrate strong in-distribution (ID) performance, th
arXiv:2607.08681v1 Announce Type: new Abstract: As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustwo
arXiv:2603.23571v2 Announce Type: replace-cross Abstract: Effective navigation intelligence relies on long-term memory to support both immediate generalization and sustained adaptation. However, exist
arXiv:2607.08625v1 Announce Type: new Abstract: Consumer-facing health chatbots powered by large language models (LLMs) are increasingly used for symptom assessment. However, chatbot development and e
the sun is out today To celebrate the launch of GPT-5.6 Sol, we will reset the rate limits again (twice) across ChatGPT Work and Codex over the next 24 hours. We want you to have the time to truly try
This was a critical early paper on AI & work, showing that entrepreneurs getting advice from GPT-4 had higher profit margins if they were high performing, but did worse if they were already in trouble
arXiv:2607.08201v1 Announce Type: cross Abstract: Large-vocabulary instance segmentation is constrained by long-tailed category distributions and fine-grained inter-class ambiguity. While data synthes
arXiv:2607.08395v1 Announce Type: cross Abstract: Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-lived software systems. Unlike traditional chat assi
arXiv:2510.04100v2 Announce Type: replace-cross Abstract: Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardiz
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
arXiv:2606.16447v2 Announce Type: replace-cross Abstract: Imitation learning has enabled highly-dexterous robotic manipulation from RGB observations. Policies trained with these methods, however, typi
arXiv:2607.08646v1 Announce Type: cross Abstract: As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Model
arXiv:2607.08267v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) increasingly rely on visual grounding capabilities to localize task-relevant targets from diverse instructions in comple
arXiv:2603.18078v2 Announce Type: replace Abstract: We present the Variational Phasor Circuit (VPC), a deterministic classical learning architecture on the continuous S^1 unit-circle manifold. Inspire
arXiv:2607.08489v1 Announce Type: cross Abstract: Vision-language models excel at video captioning, yet typically generate descriptions that fail to capture individual viewers' attention. We propose V
arXiv:2607.08729v1 Announce Type: new Abstract: Multi-object tracking (MOT) has achieved strong performance on benchmarks dominated by short video sequences. However, such datasets do not adequately e
arXiv:2607.08662v1 Announce Type: cross Abstract: Large language model (LLM)-based web search agents are transforming information seeking from simple factoid question answering into complex, deep-and-
When GPT-5 came out, I created a procedural brutalist city builder as a demo (you can see it in the quoted tweet) I used GPT-5.6 Sol in Codex to do the same thing, touching no code. Less than a year..
arXiv:2607.08535v1 Announce Type: cross Abstract: An LLM-as-judge score can move even when the candidate responses stay fixed, simply because the evaluator has changed. We treat this evaluator-replace
This post shares a Wordle game result showing the player solved puzzle #1,846 in four attempts, using the emoji-based grid system to display their guessing pattern and final correct answer. The colore
arXiv:2607.08122v1 Announce Type: new Abstract: Workload-based differentially private (DP) synthetic data methods privately measure aggregate queries and post-process the noisy answers into synthetic
Cameron Faulkner / The Verge: Xreal launches $299 A01 Plus AR glasses, weighing just 62 grams and featuring 1080p micro OLED panels with a 120Hz refresh rate and a 50-degree field of view — The A01 Pl
Yesterday, we made GPT-5.6 Sol Ultra generally available. Today, we're sharing that it produced a proof of the 50-year-old Cycle Double Cover Conjecture using 64 subagents in just under one hour. We'r
Actually I did a quick test. I like the ChatGPT Work/Codex split better than Claude Cowork/Code. The interface is much more unified. The functionality is effectively the same. The chat history is shar
arXiv:2607.06590v1 Announce Type: new Abstract: Preserving and revitalising traditional textiles such as Ulos, a cultural heritage of the Batak ethnic group in North Sumatra, Indonesia, requires balan
arXiv:2607.07637v1 Announce Type: new Abstract: This work presents a novel approach for adapting neural network architecture along the depth based on a posteriori error estimation. By formulating neur
Anthropic: Anthropic debuts a “reflection” dashboard in beta for Free, Pro, and Max users with memory turned on, to track their Claude activity over 1, 3, 6, or 12 months — Today we're introducing, in
arXiv:2607.06639v1 Announce Type: cross Abstract: On modular arithmetic, a network's embedding keeps compressing for tens of thousands of steps after it has already generalized. Reading effective rank
llama.cpp is an open-source software library that performs inference on various large language models , and b9934 represents a specific build release in the project's continuous versioning system. The
arXiv:2607.07050v1 Announce Type: new Abstract: Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy d
Jarred Sumner / bun.com: Bun's creator says he rewrote Bun from Zig to Rust using a Claude Fable 5 prerelease version in 11 days, noting it would've taken three engineers “about a year” — Disclosure:
Ivan Mehta / TechCrunch: Character.AI launches three human-written, AI-generated microdramas, whose characters users can chat with, and aims to eventually let users make their own shows — Microdramas
ChatGPT Work == Claude Cowork ChatGPT Codex == Claude Code I kinda wish OpenAI created a single unified app surface for all work, coding or not, even though I get the UI/UX would be different Introduc
ChatGPT Work is powered by GPT-5.6. GPT-5.6 makes ChatGPT state of the art at reasoning through complex tasks and creating materials that match your templates, reference files, and preferred style. Ju
ChatGPT Work reflects a shift in how people are using AI, moving beyond just answering questions to getting real work done across web, mobile, and desktop. You can ask ChatGPT Work to take on entire w
check this out! you can get some amazing things done. codex is the core of our new work product and what makes it so good. codex is not going anywhere. Introducing ChatGPT Work, a new agent in ChatGPT
Claude Code can edit a video in minutes. Friend took 7 videos totaling 25 minutes and just edited it down to a perfect 10min video for her friend's wedding in 2 prompts. She uploaded all the raw clips