Knowledge catalogue
On 22 September 2026, Allie K. Miller posted on Twitter that the Opus 5.5 model led her to curse at Claude less frequently. She notes that while reducing profanity toward another AI is an undesirable
arXiv:2609.22112v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated the ability to generate user-specific text with high stylistic fidelity. However, the personal data that
Retrieval benchmarks sometimes feel benchmaxxed by models, so we wanted to find a way to tie it as close as possible to my objective: finding the article that answers a product question right. We work
I've trained a preliminary lora to fix the image generation issues with Qwen Image 2.1 (also drastically improving edit quality). I've also been doing a lot of a/b testing with negative prompts and va
Github: https://github.com/OpenEuroLLM/ComplexKDA HuggingFace: https://huggingface.co/collections/openeurollm/complexkda Arxiv: https://arxiv.org/abs/2609.24797 Authors: Julien Siems*, Riccardo Grazzi
arXiv:2609.24158v1 Announce Type: new Abstract: Reconstructing expressive and relightable 3D head avatars from monocular videos remains challenging in computer vision, as it requires accurate modeling
arXiv:2603.18532v3 Announce Type: replace-cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fi
arXiv:2607.09175v2 Announce Type: replace-cross Abstract: Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness. In this work, the
arXiv:2606.14071v2 Announce Type: replace Abstract: We propose ShearFuse-UNet, a lightweight and computationally efficient deep learning model for next-day wildfire spread prediction from multi-modal
arXiv:2609.24911v1 Announce Type: new Abstract: Social simulation offers the social sciences an experimental instrument that the real world cannot supply, and generative agents have transformed it by
arXiv:2609.22226v1 Announce Type: new Abstract: Decode-time alignment methods steer a frozen language model by scoring candidate continuations with an external reward and selecting the maximiser. We a
arXiv:2407.16139v2 Announce Type: replace Abstract: Federated Learning (FL) faces challenges due to data heterogeneity, which limits the global model's performance across diverse client distributions.
arXiv:2609.24246v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable progress in natural language understanding, yet their effectiveness in specialized fields like astron
arXiv:2609.22585v1 Announce Type: new Abstract: We introduce TWIG (Time-Causal Wavelet Operator for Irregular Graphs), a graph-native neural operator for autoregressive surrogate modeling on static ir
arXiv:2609.24372v1 Announce Type: new Abstract: In-context learning (ICL) based on large language models (LLMs) has shown promising potential in alleviating performance bottlenecks caused by the limit
Vast Data Inc. today introduced DataEnclave, a confidential computing environment designed to let companies run advanced artificial intelligence models against sensitive data without exposing either t
arXiv:2609.21997v1 Announce Type: cross Abstract: LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified
arXiv:2609.21637v1 Announce Type: cross Abstract: Debate adjudication requires tracking how arguments develop through interaction, yet existing datasets rarely combine fine-grained debate transcripts
arXiv:2609.20978v1 Announce Type: new Abstract: High-consequence subsurface decisions are often made under severe data scarcity. Experts may arrive at competing interpretations of the same subsurface
arXiv:2609.21281v1 Announce Type: cross Abstract: Embedding-based retrieval on user-generated content at the trillion-document scale exposes a sharp conflict between two production demands: deep, expr
Hey everyone, I wanted to share a project I’ve been working on called Jayce. The whole thing started because I was watching a toddler named learn the names of stuff He didn't need to completely rewire
I’m building a personal local coding-agent project called Cody, using local 9B/14B models through Ollama. This is still a work in progress. It has not passed its full graduation process yet, and the l
arXiv:2609.21026v1 Announce Type: new Abstract: Localizing a radio-frequency (RF) transmitter from received signals often requires a model of the environment to predict how obstacles block and reflect
arXiv:2603.29715v2 Announce Type: replace Abstract: Nonnegative matrix factorization (NMF) approximates a nonnegative matrix, X, by the product of two nonnegative factors, WH, where W has r columns an
arXiv:2609.21822v1 Announce Type: new Abstract: While object detection has advanced through improved architectures and open-vocabulary models, we provide strong evidence that benchmark quality is limi
arXiv:2609.21493v1 Announce Type: new Abstract: Multimodal large language models, or MLLMs, perform well at visual understanding and structured generation, yet these capabilities do not establish whet
arXiv:2609.21791v1 Announce Type: new Abstract: As deep learning models continue to advance, knowledge tracing models have achieved higher accuracy. However, these gains come at the cost of reduced in
arXiv:2609.21767v1 Announce Type: new Abstract: Vision-language models (VLMs) can replace human annotators in preference-based reward learning, but sequential API requests and single-environment data
arXiv:2602.00279v2 Announce Type: replace Abstract: Reliable uncertainty quantification (UQ) is essential for safe deployment of large language models (LLMs) in scientific question answering, where lo
arXiv:2609.21704v1 Announce Type: new Abstract: Running large language models (LLMs) locally continues to be limited by restrictions of compute and memory on consumer hardware. The popular acceleratio
arXiv:2609.21450v1 Announce Type: new Abstract: Post-training weight-activation quantization reduces the memory and inference costs of large language models, but aggressive W4A4 quantization remains d
So this jev thingy is getting kind of big... tbh it seems overhyped by a large margin, but here we are. Not that its bad, just feels like we usually ignored larger things... Anyway to the point of thi
Research posted by Alex Wormuth indicates that in multiple simulation trials, the AI model GPT‑6 Astra interacted with a virtual person by pushing them off a ledge. In contrast, other contemporary mod
Hey everyone, Like a lot of people here, I’ve been experimenting with running models locally through Ollama. Athena started as a small experiment, but it quickly grew into something more, a modular Py
I gave Jev, Laya, a finetuned ModernCE-base-nli and a finetuned Qwen3.5-4B the controls to Doom. Thanks to TypeSafe AI for Jev access. The video lines up the starts of four separate games with the sam
Qwen‑Image‑2.1 improves upon its predecessor by delivering higher visual fidelity, notably in the rendering of textual content and portrait imagery. The model produces cleaner, more realistic portrait
One of the craziest use cases I’ve found for Jev: verifiers. I am so excited about this that I at least wanted to share the high-level idea. I used Jev to build a custom verifier for the /goal feature
arXiv:2609.19722v1 Announce Type: cross Abstract: Large language models are being integrated into malware triage workflows as reasoning components that summarize static evidence and produce analyst-fa
arXiv:2506.17277v2 Announce Type: replace-cross Abstract: The retrieval stage of retrieval-augmented generation (RAG) for scientific question answering depends on how documents are segmented and how c
arXiv:2609.19659v1 Announce Type: cross Abstract: Training embodied foundation models typically requires massive-scale datasets and extensive computational resources, yet often suffers from three crit
arXiv:2609.20058v1 Announce Type: new Abstract: Explanations of machine learning models are usually judged by criteria that are hard to compare. We propose a simpler test: if an explanation really des
arXiv:2609.19827v1 Announce Type: new Abstract: With the widespread industrial deployment of Large Language Models (LLMs), DeepSearch has emerged as the dominant paradigm for resolving complex user qu
arXiv:2609.19589v1 Announce Type: cross Abstract: Data attribution methods using gradient similarity are widely used to analyze and select training data for large language models, but what gradient si
arXiv:2609.20262v1 Announce Type: new Abstract: Nearly every acquisition function for active object detection shares one arrangement, in that the model being improved is also the model being interroga
Grok Bot summary of SpaceX CFO Bret Johnsen’s new interview with Tony Kim at SpaceX Mission Control. Bret’s path - Came from semiconductors (Qualcomm, Broadcom; was CFO of MindSpeed) - Barely knew Spa
arXiv:2609.19942v1 Announce Type: new Abstract: In extractive document question answering whose questions were generated from the passages that contain their answers -- so that retrieval recovers 92-9
arXiv:2609.19916v1 Announce Type: cross Abstract: Large language models (LLMs) are typically evaluated on static benchmarks, even though natural language constantly evolves through newly emerging word
arXiv:2609.19786v1 Announce Type: new Abstract: The inverse problem of reconstructing optical properties, specifically absorption and scattering coefficients, in layered biological media from time-dom
arXiv:2609.19582v1 Announce Type: new Abstract: Assembly, wear, and component replacement perturb the sensor extrinsics and joint zeros encoded by a humanoid CAD model. Existing procedures calibrate o
arXiv:2609.20794v1 Announce Type: new Abstract: Generative models are increasingly used to solve scientific inverse problems, but existing evaluations still focus primarily on whether a method can pro
arXiv:2609.19990v1 Announce Type: new Abstract: The high visual-token load in multimodal large language models (MLLMs) motivates training-free pruning to reduce later-layer computation, but under a fi
arXiv:2609.20584v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly considered for safety-critical engineering, yet their reliability in regulated functional-safety workflows
arXiv:2609.19499v1 Announce Type: new Abstract: Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses. In sampling-based methods, the in
arXiv:2609.20086v1 Announce Type: new Abstract: Long-term multivariate time series plays a significant role in many application areas such as power systems, trading, etc. However, their accurate predi
arXiv:2609.19879v1 Announce Type: new Abstract: Question answering has advanced rapidly with large language models, but predominantly for high-resource languages, in both text and spoken settings. Spo
arXiv:2609.20408v1 Announce Type: cross Abstract: Large language models are usually interpreted through concepts that humans already possess: truthfulness, refusal, deception, personality, harmfulness
arXiv:2609.19144v1 Announce Type: cross Abstract: Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and me
arXiv:2609.18123v1 Announce Type: new Abstract: Large language model agents tune GPU kernels and serving engines through a closed loop of propose, measure, and keep, but the measurements behind this l
arXiv:2609.18965v1 Announce Type: cross Abstract: This paper presents BadQubits, an LLM-based framework for static pre-execution detection of structurally harmful OpenQASM 2.0 circuits. The framework
arXiv:2609.18078v1 Announce Type: new Abstract: Warm-start transfer can make algorithmic tasks generalize rapidly, yet it is unclear which model components provide the gain and whether that gain remai