Knowledge catalogue
arXiv:2609.05097v1 Announce Type: cross Abstract: AI-driven de novo molecular design offers a promising route to accelerate early-stage drug discovery by generating novel ligands directly within targe
arXiv:2609.05385v1 Announce Type: new Abstract: LLM decision components that can operate within agent workflows often produce action-relevant recommendations or judgements together with explanations.
arXiv:2603.13320v2 Announce Type: replace-cross Abstract: Nepali, a low-resource language, faces significant challenges in building an effective information retrieval system due to the unavailability
arXiv:2609.04466v1 Announce Type: new Abstract: In Geometric Deep Learning, inductive biases serve two primary functions: enforcing manifold constraints and embedding relational priors. Currently, rep
How it works. The model being tested is given a server capable of running it's weights and full context. That server is placed in a median priced apartment. The AI is given a bank account with for ren
arXiv:2603.05617v2 Announce Type: replace Abstract: We present NotAI.AI, an explainable AI-generated text detection system. Instead of returning only a binary label or confidence score, the system sho
arXiv:2609.05139v1 Announce Type: new Abstract: Long-form literary narratives pose a distinctive information-processing challenge for retrieval-augmented generation: relevant evidence is distributed a
arXiv:2609.04348v1 Announce Type: new Abstract: Object-centric visual representations are important for physical-world perception, but existing visual pretraining methods often capture semantic catego
arXiv:2609.04458v1 Announce Type: new Abstract: Data collected during aerial and spaceborne imaging spectroscopy campaigns enables the detection of transient events such as trace gas emissions. Howeve
arXiv:2609.04835v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used not only to retrieve information, but to answer questions, explain, teach, and support inquiry. In su
arXiv:2609.04379v1 Announce Type: new Abstract: This paper considers the energy landscape of the t-SNE algorithm. While this algorithm has enjoyed broad adoption, the non-convexity of the associated e
On the quote at the top, I agree with @geoffreyhinton 100% 'We would be very foolish to develop superintelligence now, when there is no scientific consensus it can be developed safely and controllably
arXiv:2609.04921v1 Announce Type: cross Abstract: Diffusion probabilistic models can capture the multi-modal, interaction-rich distribution of joint future trajectories in driving scenes. We show that
arXiv:2609.05260v1 Announce Type: new Abstract: Natural-language instruction changes can directly alter robot behavior. A reliable embodied system should preserve its action when the task is unchanged
arXiv:2609.05298v1 Announce Type: cross Abstract: Cooperative multi-agent reinforcement learning (MARL) systems rely on past experience for learning coordinated behaviour, but this experience may beco
arXiv:2609.04607v1 Announce Type: new Abstract: Three-dimensional scene graphs (3DSGs) have emerged as a promising approach for building geometrically grounded, semantically informed, hierarchical gen
arXiv:2609.05318v1 Announce Type: new Abstract: Building on the pioneering paper of Kearns, Roth, and Ryu (SODA'26), we study information aggregation in a networked learning model. The model captures
arXiv:2609.04577v1 Announce Type: new Abstract: We investigate how optimizers scale across the overtraining axis and show that relative optimizer performance and optimal hyperparameters change substan
arXiv:2602.06761v2 Announce Type: replace-cross Abstract: Fetal echocardiography is essential for detecting congenital heart disease (CHD), facilitating pregnancy management, optimized delivery planni
Ouch: “Nvidia is building the most concentrated bet on a single technology cycle that any company has ever made. If these valuations keep climbing, Jensen looks like a genius. If they don't, Nvidia is
arXiv:2506.21185v3 Announce Type: replace Abstract: 3D semantic occupancy prediction is crucial for autonomous driving, providing a dense, semantically rich environmental representation. However, exis
arXiv:2609.05212v1 Announce Type: cross Abstract: Forecasting time series accurately is critical for applications with complex data ranging from energy systems to healthcare and finance. Among current
arXiv:2609.04832v1 Announce Type: new Abstract: Client heterogeneity creates both an opportunity and a risk in personalized federated graph learning. Knowledge held by other subgraphs may complement a
arXiv:2609.04620v1 Announce Type: new Abstract: Personalized autonomous packing requires robots to account for resident preferences that cannot be inferred from scene geometry alone. Expert teleoperat
arXiv:2609.04837v1 Announce Type: new Abstract: Single domain generalization (SDG) aims to learn a model from one labeled source domain that generalizes to unseen target domains. A common strategy is
I've built and open-sourced ParaRNN, a PyTorch/Triton library that parallelizes the training of non-linear recurrent architectures across time using Newton-Raphson iterations mapped to associative pre
arXiv:2512.06813v3 Announce Type: replace-cross Abstract: High-performance concrete (HPC) requires complex mix design decisions involving interdependent variables and practical constraints. While data
arXiv:2609.04484v1 Announce Type: cross Abstract: This paper investigates structural priming in language model (LM) production, examining how preceding structural context influences sentence completio
arXiv:2609.04476v1 Announce Type: new Abstract: Performance modeling is central to hardware design and software optimization, yet constructing these models requires structured reasoning about computat
arXiv:2603.25685v2 Announce Type: replace-cross Abstract: Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promisin
arXiv:2609.04773v1 Announce Type: cross Abstract: Distillation is common in LLM post-training, where on-policy knowledge distillation (OPKD) uses student-generated trajectories to prepare the student
arXiv:2609.04598v1 Announce Type: cross Abstract: We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary knowledge and clinical reasoning in large language
arXiv:2609.05194v1 Announce Type: cross Abstract: The number of discrete class-separability jumps observed during ResNet finetuning is examined empirically as a predictor of final test accuracy. Acros
arXiv:2609.04943v1 Announce Type: new Abstract: Recent benchmarks such as PowerGraph provide large collections of power-grid graphs for cascading-failure classification. Graph neural networks (GNNs) a
arXiv:2609.04516v1 Announce Type: cross Abstract: Recent work on controllable music generation has focused on autoregressive models, leaving diffusion-based systems comparatively underexplored. We pre
arXiv:2609.04715v1 Announce Type: new Abstract: Personalizing large language models (LLMs) is essential for delivering AI assistance that aligns with individual users' styles, intents, and preferences
arXiv:2603.05623v2 Announce Type: replace-cross Abstract: Camera-LiDAR fusion is widely used in autonomous driving to enable accurate 3D object detection. However, bird's-eye view (BEV) fusion detecto
arXiv:2609.04693v1 Announce Type: new Abstract: Urban air quality can vary significantly along transit corridors, necessitating high-resolution monitoring. This work introduces a novel mobile-sensing
arXiv:2609.05235v1 Announce Type: cross Abstract: Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language
arXiv:2609.04867v1 Announce Type: cross Abstract: Text-to-audio-video (T2AV) generation has advanced rapidly, but its evaluation still underestimates the audio modality. Existing benchmarks either tre
arXiv:2609.04382v1 Announce Type: cross Abstract: We present a systems-security case study of a two-node split-LLM training system whose privacy evaluation passed while leaving an observable channel u
arXiv:2609.05094v1 Announce Type: new Abstract: Electroencephalogram (EEG) visual decoding aims to recover visual semantics from non-invasive neural time-series signals, for which robust alignment bet
arXiv:2603.21438v3 Announce Type: replace Abstract: To discover the weaknesses of LLMs, researchers often embed prompts into a vector space and cluster them to extract insightful patterns. However, ve
arXiv:2609.04793v1 Announce Type: new Abstract: Proteins perform diverse cellular functions, and even single amino-acid substitutions can alter stability, activity, or molecular interactions. Protein
arXiv:2609.04265v1 Announce Type: new Abstract: Existing post-hoc explainers for machine learning classifiers primarily focus on feature attribution, assigning importance scores to individual features
arXiv:2609.05249v1 Announce Type: cross Abstract: As spaceborne computing systems increasingly rely on neural network (NN) accelerators, the opacity of commercial, black-box architectures severely res
arXiv:2609.05038v1 Announce Type: new Abstract: Species identification in camera trap images has been widely studied, but key ecological modeling tasks such as species abundance or density estimation
arXiv:2609.05039v1 Announce Type: cross Abstract: Quantum software development is iterative and error-prone. Noisy hardware and repeated re-execution make experiment tracking, provenance, and reproduc
arXiv:2509.21889v3 Announce Type: replace Abstract: Existing evaluations of foundation models predominantly focus on output correctness, treating interaction as a static exchange of information. Howev
arXiv:2211.12337v4 Announce Type: replace Abstract: The theory of magnitude provides a mathematical framework for quantifying and maximizing diversity. We apply this framework to formulate quality-div
arXiv:2609.04263v1 Announce Type: cross Abstract: Low-bit key--value (KV) caches reduce the memory required for autoregressive decoding, but the resulting quality loss depends on the model and quantiz
arXiv:2609.04271v1 Announce Type: new Abstract: Wi-Fi-based human activity recognition (HAR) has become an important part of integrated sensing and communications, paving the way for a range of contex
The strongest argument I see for continuing to train much smarter models quickly is the need to build defensive systems against the dangers posed by other AI. [...] We will need powerful, aligned AI f
I just tried to run Qwen 3.8 27B 4bit qwant on 5060ti 16GB and got terrible results. With Qwen 3.6 I got something around 15-20 tok/s. Are there any combination of parameters or tweeks how to push the
Long time user of 3.6 27b, switched over to Next Flash since it's a logical step up even from 3.8 27b. It's soooo verbose, i'm talking 13 minutes of thinking time on single turn coding requests at app
Since the Qwen3.5 0.8B model is an interesting one for small specialized fine tunes, I was curious how fast it can run on CPUs. Why CPUs? Mainly because I want to use it as a local dictation cleanup m
I’ve been setting up an M1 Max Mac Studio (24-core GPU, 32GB unified memory) as a local LLM server and wanted to compare MLX vs llama.cpp on Qwen3.8-27B. I tried to keep the model footprint and benchm
My XFX Radeon RX 7900 GRE 16GB Vram GPU struggles with models over 20B size. I added my Radeon RX 480 8GB Vram GPU to the system and ran a few benchmarks using llama.cpp Ubuntu Vulkan build 10453. htt
arXiv:2609.04649v1 Announce Type: new Abstract: We present DiT Readout (ReaDiT) Guidance, a lightweight framework for controlling generation with Diffusion Transformer (DiT) models via their internal
arXiv:2609.05202v1 Announce Type: cross Abstract: Multi-modal learning has demonstrated strong potential in medical applications by integrating heterogeneous data sources such as medical imaging, clin