Knowledge catalogue
arXiv:2511.04473v3 Announce Type: replace-cross Abstract: Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While va
arXiv:2609.22241v1 Announce Type: new Abstract: We present H2LooP Telecom Model v1, a domain-specialized large language models fine-tuned for the telecommunications industry. We release two domain-ada
arXiv:2609.24778v1 Announce Type: new Abstract: Learning robot manipulation policies from human video demonstrations constitutes a promising avenue for scalable robot learning. However, comparing diff
arXiv:2609.24308v1 Announce Type: new Abstract: Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, inte
arXiv:2609.24095v1 Announce Type: new Abstract: While deep learning has enabled language decoding from intracranial brain recordings, extending this capability to non-invasive recordings remains an un
I keep trying to get it to write code and test simpel stuff but it never finsihes conversation its always stopping mid way. i installed it through qwen > ollama. currently removed it and trying to rei
arXiv:2609.22139v1 Announce Type: cross Abstract: Automatic modulation classification (AMC) of received radio signals is prudent for further signal processing tasks such as communication monitoring, c
Hi everyone, I wanted to ask you a question. I’m developing an app, and I’m currently putting together a list of the best AI models, especially, but not necessarily, in GGUF format and using Q4_K_M qu
arXiv:2609.22264v1 Announce Type: cross Abstract: State-of-the-art models for audio-driven digital human generation have achieved photo-realistic results in talking-head synthesis. However, extending
arXiv:2609.24276v1 Announce Type: new Abstract: Hyperbolic vision-language models (VLMs) represent image and text features in a geometry naturally suited to hierarchy, but their adaptation to downstre
arXiv:2609.24634v1 Announce Type: new Abstract: Nitrogen dioxide (NO2) is a common air pollutant, released into the atmosphere through the incomplete burning of fossil fuels, and associated with respi
In a tweet posted on September 22, 2026, OpenAI noted that increasing usage limits while lowering costs gives users greater flexibility and more room to iterate on their projects. This announcement hi
arXiv:2409.07107v3 Announce Type: replace Abstract: Robotics simulators have improved significantly in computational speed and scalability, enabling them to generate years of simulated data for comple
arXiv:2609.23431v1 Announce Type: new Abstract: Human-object interaction (HOI) detection requires grounding an interacting human-object pair and recognizing the verb that links them, often under sever
arXiv:2601.22033v2 Announce Type: replace Abstract: Holography, in the form of the anti-de Sitter/conformal field theory (AdS/CFT) correspondence, offers a natural setting for generative modelling. Da
arXiv:2609.22788v1 Announce Type: new Abstract: Video foundation models now reach human-level accuracy on physical-reasoning benchmarks, yet such tasks require predicting unobserved physical outcomes.
arXiv:2602.13718v2 Announce Type: replace Abstract: Generative policies for robotic manipulation must balance action accuracy with inference latency. We present HybridFlow, a three-stage policy infere
arXiv:2609.24564v1 Announce Type: new Abstract: CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing CLIP's text encoder
You know the thing where you ask a chatbot what's wrong with your plan and it goes 'there are three problems here' and problem three is clearly the runt of the litter? There's a word for that now. An
I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached. TLA+ also works well. I sometimes combine L
arXiv:2609.24556v1 Announce Type: cross Abstract: Principal Component Analysis (PCA) minimises aggregate reconstruction error, which can inadvertently represent majority subgroups with substantially h
arXiv:2609.24228v1 Announce Type: new Abstract: Text-to-image (T2I) models are typically evaluated for bias using slot-based templates such as ``a photo of a [profession]''. Such templates probe only
Impressive paper showing how much the harness changes a coding agent's results. Harnesses do play a huge role in what you are getting out of the models. GPT-5.5 was run inside both Claude Code and Cod
arXiv:2609.22783v1 Announce Type: new Abstract: We study differentially private covariance estimation in operator norm for mean-zero sub-Gaussian distributions with unknown covariance support and at m
arXiv:2609.22199v1 Announce Type: new Abstract: Transformer-based large language models often suffer from inter-layer parameter redundancy, where functional transformations are redundantly learned acr
In our evaluations, we see that GPT-6 Sol reads about 17% less context than GPT-5.6 Sol to reach the same score, and rarely leaves a repo with failing tests after its last edit. GPT-6 Luna’s biggest g
arXiv:2607.15577v2 Announce Type: replace Abstract: Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-
arXiv:2609.24511v1 Announce Type: new Abstract: Contact-rich precision insertion is a key manipulation skill in robotic assembly. Tight clearances make insertion more sensitive to alignment errors and
Following a successful private preview, we’re thrilled to open DigitalOcean Managed Agents to everyone. Teams can now deploy their preferred agent harness (like OpenCode, Codex CLI) or bring their own
arXiv:2609.22152v1 Announce Type: new Abstract: Imagination performs as a high-level function of large language models (LLMs) which determines the potential of how an LLM creates unseen or creative co
I am trying out a few fine-tunes of Qwen 3.5 9B @ IQ4_XS @ 131K context and trying to go mostly local (free beats cheap, after all). However, it is much slower than at, say 16K context, even when I am
arXiv:2609.24646v1 Announce Type: new Abstract: On-policy self-distillation fine-tuning (SDFT) learns new skills from demonstrations while reducing forgetting, but it always distils toward the full de
arXiv:2609.23516v1 Announce Type: new Abstract: Structural causal models for time series recover contemporaneous and lagged effects, but most methods require complete observation windows and become mi
arXiv:2609.24954v1 Announce Type: cross Abstract: Pharmaceutical process characterization is central to Quality by Design because it defines how variations in process parameters affect the ability to
arXiv:2609.23183v1 Announce Type: new Abstract: Inverse design of RF and electromagnetic (EM) circuits is challenging because the relationship between circuit layout and electrical response is non-uni
arXiv:2609.23267v1 Announce Type: new Abstract: The visual modality, i.e., images, plays a key role in multi-modal entity alignment (MMEA). Existing approaches often directly fuse the image with other
arXiv:2609.23067v1 Announce Type: new Abstract: Referring surgical video instrument segmentation (RSVIS) aims at segmenting the instrument in a surgical video, given a textual description. Despite rec
arXiv:2609.22092v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a low-cost and non-invasive signal source for dementia screening, yet existing EEG-based studies remain difficult to c
arXiv:2609.22338v1 Announce Type: cross Abstract: This tutorial provides a unified view of the emerging area of bilinear learning and control. Using linear systems as a benchmark, it explains what fun
arXiv:2609.24947v1 Announce Type: new Abstract: Neural operators evaluate parametric partial differential equations cheaply but degrade sharply outside their training distribution. Physics-informed ne
arXiv:2609.24172v1 Announce Type: new Abstract: Legends are fundamental to chart understanding, as reliable interpretation requires correctly binding legend entries to corresponding visual marks. Whil
arXiv:2609.22867v1 Announce Type: new Abstract: Diffusion models generate a sample by traversing a denoising trajectory, a sequence of stochastic noise-reduction steps that transforms pure noise into
arXiv:2609.24350v1 Announce Type: cross Abstract: Robotic foundation models achieve impressive performance on standard manipulation benchmarks, yet these evaluations typically assume clean, timely, an
arXiv:2609.22230v1 Announce Type: new Abstract: Counting the items in a bracketed list looks trivial, yet open-weight chat models often get it wrong. Prior work usually blames input bottlenecks such a
arXiv:2609.22700v1 Announce Type: new Abstract: Step-level reasoning evaluators are commonly based on autoregressive language models, whose causal attention restricts each step representation to the p
**llm-anthropic 0.29** is a software package that offers programmatic access to Anthropic’s large language models, including the Claude series. It handles authentication, API requests, and response pa
arXiv:2609.22642v1 Announce Type: cross Abstract: We develop inference for manifold-valued population minimizers when each observation belongs to a different participant and only locally private messa
arXiv:2609.22782v1 Announce Type: new Abstract: Steering with SAE features requires per-feature coefficient tuning, which currently demands intervention sweeps. We ask whether properties of the SAE it
Now that OpenAI has officially paused new sign-ups and upgrades for the ChatGPT Pro 200 (Pro 20X) plan, I’m looking for a solid alternative for enterprise-level development. For those unfamiliar: Code
arXiv:2609.24979v1 Announce Type: new Abstract: On-device large language models (`LLMs'), e.g. running on mobile phones, are ripe for improvement via personalization. The limited compute resources of
arXiv:2609.23003v1 Announce Type: new Abstract: We present M3GA-Wild, the first benchmark for multi-modal, multi-session ground-to-aerial place recognition in forests. M3GA-Wild unifies and extends ex
arXiv:2609.23371v1 Announce Type: new Abstract: Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persistent i
Mars Sample Return mission is dead in the latest funding agreement. Which means China will likely beat the US to returning the first samples from Mars. Perseverance has collected the best samples it c
arXiv:2609.24161v1 Announce Type: cross Abstract: As LLM agents increasingly interact with external tools through standardized protocols such as MCP, tool-interface design becomes a critical yet under
arXiv:2609.23085v1 Announce Type: cross Abstract: Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajectori
arXiv:2609.22220v1 Announce Type: new Abstract: Benchmarks for LLM-generated GPU kernels decide correctness with a few random inputs and a loose floating-point tolerance, and their verdicts now feed l
arXiv:2609.24455v1 Announce Type: new Abstract: Intelligent transportation systems require Incremental Learning (IL) to continually improve their overall performance in dynamic environments. However,
arXiv:2603.00842v2 Announce Type: replace Abstract: Biomedical multimodal assistants have the potential to unify radiology, pathology, and clinical-text reasoning, yet a critical deployment gap remain
arXiv:2609.24259v1 Announce Type: new Abstract: The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over
arXiv:2502.01562v3 Announce Type: replace Abstract: As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability to learn to master multiple complex tasks throu