Knowledge catalogue
arXiv:2609.35082v1 Announce Type: new Abstract: Group-based reinforcement learning such as GRPO trains LLM agents by comparing rollouts sampled for each task, without a learned critic. In long-horizon
arXiv:2609.35096v1 Announce Type: new Abstract: Deepfake detection methods have become increasingly effective yet most provide limited insight into the evidence behind their predictions. However, in f
arXiv:2609.33298v1 Announce Type: new Abstract: In many settings, post-training need not create the target behavior from scratch: the base model can already produce it, but not reliably. This shifts p
arXiv:2609.34058v1 Announce Type: new Abstract: AI systems often feel brittle and fragmented. A large language model (LLM) may correctly explain a concept but fail to apply it, or follow safety instru
arXiv:2609.31882v1 Announce Type: new Abstract: Reward-based diffusion fine-tuning faces practical challenges when desirable outcomes are rare or conditioning corrections are costly to estimate. In th
arXiv:2609.35289v1 Announce Type: new Abstract: Denoising Diffusion Probabilistic Models have shown remarkable performance in unconditional image generation. In order to generate images with desired s
arXiv:2609.35634v1 Announce Type: new Abstract: Electrocardiogram (ECG) recordings are corrupted by non-stationary noise sources that degrade diagnostic reliability, particularly in ambulatory and lon
arXiv:2609.35242v1 Announce Type: new Abstract: Scalable Vector Graphics (SVG) are essential for modern industrial Computer-Aided Design (CAD). However, existing autoregressive SVG generation models a
arXiv:2609.34921v1 Announce Type: new Abstract: Predicting Drug-Target Interactions~(DTIs) is a central task in computational drug discovery, with direct applications in virtual screening, drug repurp
arXiv:2609.35704v1 Announce Type: new Abstract: Video generation must account for two sources of motion, one induced by the observer's camera path and the other caused by scene dynamics. An ideal came
arXiv:2609.32177v1 Announce Type: new Abstract: Three-dimensional (3D) Gaussian splatting (3D-GS) has emerged as a promising technique for large-scale scene reconstruction due to its high rendering ef
Forlinx Embedded has listed an M.2 AI accelerator card based on Rockchip’s RK1820 and RK1828 processors, providing 20 TOPS of INT8 computing performance and up to 5GB of integrated DRAM. The module us
arXiv:2609.34679v1 Announce Type: new Abstract: Bipartite matching is a fundamental problem in game theory and market design. Classical approaches such as Gale--Shapley assume complete preferences and
arXiv:2609.34362v1 Announce Type: new Abstract: World Action Models (WAMs) augment robot action generation with future visual supervision. Existing WAMs commonly fuse main and wrist observations into
arXiv:2609.32158v1 Announce Type: new Abstract: Moving obstacles can block a previously clear route while a quadruped robot executes a motion command. We investigate whether predicting changing cleara
arXiv:2609.35042v1 Announce Type: cross Abstract: Martian weather forecasting is important for future exploration, but atmospheric behaviour on Mars combines spatial, temporal, vertical, and dust-driv
arXiv:2609.35267v1 Announce Type: new Abstract: Large-scale 3D multi-agent path finding becomes increasingly difficult under dense traffic. Priority Inheritance with Backtracking (PIBT) scales well, b
arXiv:2609.32838v1 Announce Type: new Abstract: Predicting smooth dynamics and collisions requires modeling continuous evolution and abrupt state changes. We introduce HamiFormer, a dual-expert diffus
arXiv:2609.31765v1 Announce Type: new Abstract: Accurate and rapid prediction of the aerodynamic drag coefficient (C_D) is essential for vehicle design, particularly during early-stage styling iterati
arXiv:2609.32426v1 Announce Type: new Abstract: For graph node classification, calibrated class probabilities are needed when confidence scores, usually the maximum predicted class probability, are us
Hugging Face Jobs usage is stonking 📈 All thanks to agents: you just need the hf CLI installed and you have access to an insane amount of hardware. Asked mine to test hundreds of code snippets from Hu
arXiv:2609.35379v1 Announce Type: new Abstract: Electroencephalography (EEG) records mixtures of brain-source activity. Even with a known anatomical forward model, experiments that excite only part of
arXiv:2609.31643v1 Announce Type: new Abstract: A principal who deploys a binary classifier with an abstention option must decide which queries the mechanism abstains on. The right choice depends on t
arXiv:2609.34786v1 Announce Type: new Abstract: Longer histories can improve time-series foundation models (TSFMs), but require substantially higher inference cost. We therefore ask whether contextual
IQuest-Q1 is a Mixture-of-Experts (MoE) model developed by IQuest for agentic coding, reasoning, and multi-step tool use. It comprises approximately 320B total parameters, with an estimated 15B parame
arXiv:2609.33874v1 Announce Type: new Abstract: JET uses pretrained language and vision-language models to select among a finite set of answers without additional training. It evaluates candidate like
arXiv:2609.34478v1 Announce Type: new Abstract: Task-specific fine-tuning can rewrite a language model's answers beyond the training task, complicating updates that must preserve existing behavior. We
arXiv:2609.35046v1 Announce Type: new Abstract: Category-level 6D pose estimation from a single RGB-D observation is inherently under-constrained, since partial visible geometry must be interpreted to
arXiv:2607.17511v2 Announce Type: replace Abstract: Large Time Series Foundation Models (TSFMs) demonstrate strong zero-shot forecasting capabilities across diverse domains. However, their application
arXiv:2609.33383v1 Announce Type: cross Abstract: The local linear minimization oracle (Ferris and Zavriev, 1996; arXiv:2605.08850), or Local LMO, solves constrained convex problems without having to
arXiv:2502.13440v2 Announce Type: replace-cross Abstract: Prevailing bioacoustic classifiers assign species labels to fixed time-frequency windows rather than to individual vocalizations. When multipl
arXiv:2609.32517v1 Announce Type: cross Abstract: The current deep learning training paradigm employs end-to-end backpropagation, regardless of the training stage, i.e. pre-training or fine-tuning. Ho
arXiv:2609.32742v1 Announce Type: new Abstract: Video super-resolution (VSR) is an ill-posed inverse problem that aims to reconstruct a high-resolution (HR) video from a noisy, low-resolution (LR) ver
arXiv:2609.34836v1 Announce Type: cross Abstract: Extending reliable nowcasting of extreme precipitation could provide critical additional time for warnings and emergency response during high-impact e
arXiv:2609.34167v1 Announce Type: new Abstract: Foundation models pre-trained on large-scale fMRI datasets have shown strong downstream performance, but at substantial data and computation cost. To in
arXiv:2609.31699v1 Announce Type: cross Abstract: A microphone on the airframe of a small multi-rotor UAV is dominated by rotor ego-noise, so spoken flight commands arrive at negative signal-to-noise
arXiv:2609.33100v1 Announce Type: new Abstract: Video models commonly use uniform grids even though visual complexity varies substantially across space and time. We introduce OctVideo, which approxima
arXiv:2609.32780v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly use sparse mixture-of-experts (MoE) to scale language-side computation, yet visual information is typically r
arXiv:2609.34653v1 Announce Type: cross Abstract: On-device streaming omni-modal inference safeguards user privacy and eliminates prohibitive per-token API costs, but faces a critical bottleneck: the
arXiv:2609.34301v1 Announce Type: new Abstract: Drug design couples property evaluation, conditional generation, structure-based design, and local optimization, yet machine learning systems typically
arXiv:2609.33562v1 Announce Type: new Abstract: Systematic out-of-distribution (OOD) generation remains a critical bottleneck for continuous-time generative models. While standard joint classifier-fre
Ornith-1.5-9B-DFlash pairs the Ornith-1.5-9B model with a DFlash draft model for speculative decoding. https://huggingface.co/ornith-ai/Ornith-1.5-9B-DFlash Ornith-1.5-397B-DFlash pairs the Ornith-1.5
arXiv:2609.35579v1 Announce Type: new Abstract: Residual stream pruning methods reduce inference cost by shrinking the model's hidden dimension, but existing approaches typically choose these dimensio
arXiv:2609.33171v1 Announce Type: cross Abstract: Latent diffusion models serve as powerful priors for solving inverse problems in image restoration, such as deblurring, inpainting, and super-resoluti
arXiv:2609.31855v1 Announce Type: new Abstract: Human demonstrations provide dense policy-level information but sometimes lack local precision. Human feedback presents accurate local critiques, but of
arXiv:2609.34466v1 Announce Type: new Abstract: Physiological foundation models encode how a signal was recorded alongside the physiology it reflects. When recording conditions are associated with dia
arXiv:2609.34784v1 Announce Type: new Abstract: Constructing a smooth approximation of an unsigned distance field (UDF) from a raw point cloud is challenging because the input provides neither surface
arXiv:2609.32469v1 Announce Type: cross Abstract: In-context learning is highly sensitive to demonstration choice, yet most methods select demonstrations using external query-demonstration similarity.
arXiv:2609.33384v1 Announce Type: new Abstract: Quantization errors in video diffusion transformers can be amplified or attenuated by subsequent denoising updates, making local reconstruction error an
arXiv:2609.35168v1 Announce Type: new Abstract: Saved checkpoints record states along a training trajectory, but generally do not determine the updates at states that would be visited under a differen
arXiv:2609.33202v1 Announce Type: new Abstract: Flow-matching models generate high-quality images and videos, but repeated neural network evaluations make sampling expensive. Skipping evaluations redu
arXiv:2609.33095v1 Announce Type: new Abstract: Generating responsive listener facial motion is an important task for embodied conversational AI. Two modeling challenges are central: accounting for th
arXiv:2609.32141v1 Announce Type: new Abstract: Deep ReLU networks are piecewise-affine mappings that partition the input space into cells, each characterized by a distinct activation pattern. This st
arXiv:2609.32389v1 Announce Type: new Abstract: Filmmakers and visual artists routinely need to compose multiple references, actors, locations, props, cultural elements, into a single coherent shot, b
arXiv:2609.33344v1 Announce Type: new Abstract: Scene Coordinate Regression (SCR) has recently emerged as a promising approach for LiDAR-based localization, achieving accurate localization without req
arXiv:2609.34701v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate enterprise workflows involving multiple specialized agents, external tools, and long-runni
arXiv:2609.31932v1 Announce Type: cross Abstract: Low-Earth-orbit (LEO) satellites are increasingly expected to perform onboard learning for applications such as disaster response and environmental mo
arXiv:2609.34863v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have approached image segmentation by reasoning about visual content and predicting target locations. Their gen
arXiv:2609.35517v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student language model with dense feedback from a stronger teacher on student-generated trajectories. Yet standard
arXiv:2609.34004v1 Announce Type: new Abstract: Equity-relevant news evolves through temporally dependent corporate events, making historical information useful only when event continuity, information