Knowledge catalogue
arXiv:2609.39625v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be u
arXiv:2609.39154v1 Announce Type: cross Abstract: Deep research tasks require agents to navigate large knowledge spaces, synthesize evidence across many sources, and adapt their plans as findings emer
arXiv:2603.26164v2 Announce Type: replace-cross Abstract: Data-centric training has emerged as a promising direction for improving large language models (LLMs) by optimizing not only model parameters
arXiv:2609.38767v1 Announce Type: cross Abstract: Training data attribution (TDA) estimates the contribution of individual training examples to model outputs. Most scalable TDA methods rely on per-exa
arXiv:2609.39222v1 Announce Type: new Abstract: High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff bet
arXiv:2609.40241v1 Announce Type: cross Abstract: Large language models (LLMs) have shown promise for recommendation reranking, but their use introduces an important tradeoff between recommendation qu
arXiv:2609.39096v1 Announce Type: new Abstract: Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows with the generated history. Existing compre
arXiv:2609.39390v1 Announce Type: new Abstract: Few-Shot Class-Incremental Learning (FSCIL) addresses the challenge of learning new classes from very limited samples while retaining knowledge of previ
Optional Bundle architecture: Schedule (session-local delayed / timed / interval reminders) was removed from the default set and made an explicit Optional Bundle. This cleanly separates “installed” fr
This is the first of a two-part series exploring how Google Cloud is bringing the foundational values of a high-performance parallel filesystem–TB/s throughput, sub-ms latency at high client scale, an
arXiv:2401.13937v3 Announce Type: replace Abstract: Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object r
arXiv:2609.39098v1 Announce Type: cross Abstract: Perceiving human motion via privacy-preserving 4D millimeter-wave (mmWave) radar is critical for next-generation human-robot interaction (HRI), where
arXiv:2609.38472v1 Announce Type: cross Abstract: Behavior cloning provides an offline route to autonomous-driving policy learning, but mean-squared-error regression is poorly matched to demonstration
arXiv:2609.39763v1 Announce Type: cross Abstract: Pretrained video foundation models encode rich semantic and spatiotemporal priors for embodied navigation, yet converting these priors into UAV motion
arXiv:2609.39526v1 Announce Type: new Abstract: Efficient action generation in vision-language-action (VLA) models requires capturing both coarse action structure and fine-grained details. Discrete ac
arXiv:2609.39326v1 Announce Type: cross Abstract: Count data pose a challenge for score-matching-based causal discovery: derivatives are unavailable, and simply replacing them with finite differences
arXiv:2609.38777v1 Announce Type: new Abstract: A central goal of vision-language model (VLM) distillation is to transfer both the teacher's language capabilities and its visual understanding. However
arXiv:2609.39449v1 Announce Type: cross Abstract: Distributionally robust optimization (DRO) studies parameter estimation under uncertainty in the underlying probability distribution and has emerged a
Evolving MLPerf Training from feature-interaction baselines to production-scale sequential recommendation with HSTU and the 560 GB Yambda-5B embedding benchmark. The post DLRMv4: The Next-Generation R
arXiv:2609.39901v1 Announce Type: cross Abstract: Goal-conditioned reinforcement learning (GCRL) relies heavily on how target goals are represented to the policy. While recent methods encode goals via
arXiv:2609.39909v1 Announce Type: cross Abstract: We introduce DoGBENCH (Documentation Generation Benchmark), to our knowledge, the first benchmark for generating and maintaining real user-facing soft
arXiv:2609.39710v1 Announce Type: new Abstract: Scientific abstracts mix contributions with background, motivation, and meta-language, so tools that read them as-is cannot separate what a field produc
arXiv:2609.38948v1 Announce Type: cross Abstract: Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present
arXiv:2609.39198v1 Announce Type: new Abstract: While Vision-Language-Action (VLA) models excel in static tasks, they struggle in dynamic environments where objects are in motion (e.g., conveyor belt
arXiv:2609.39446v1 Announce Type: new Abstract: Existing full-duplex speech benchmarks cover only subsets of real-time interaction behaviors, often under limited contextual conditions. We introduce Du
arXiv:2609.39839v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tunin
arXiv:2609.39841v1 Announce Type: new Abstract: Reconstructing dynamic driving scenes from recorded sensor data supports closed-loop evaluation of autonomous driving systems by synthesizing observatio
arXiv:2609.38335v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) are evolving from making localized code changes to developing complete software repositories. Ho
arXiv:2609.39575v1 Announce Type: cross Abstract: Generating full-body co-speech motion for humanoid robots requires coordinating speech prosody, linguistic content, and embodiment-specific motion. To
arXiv:2609.38862v1 Announce Type: cross Abstract: Safe and efficient trajectory planning is essential in autonomous driving. However, existing end-to-end approaches often fall short in both computatio
arXiv:2609.38932v1 Announce Type: new Abstract: Surface electromyography (sEMG) provides a wearable, camera-free signal for continuous hand-motion inference. Mapping muscle activity to joint kinematic
arXiv:2609.39378v1 Announce Type: new Abstract: Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving
arXiv:2609.38182v1 Announce Type: cross Abstract: Avatar-based multimodal empathetic response generation has emerged as a pivotal capability in human-centric systems, aiming to recognize user emotions
arXiv:2609.39284v1 Announce Type: cross Abstract: While large language models have achieved remarkable success in isolated code generation, authentic software engineering requires sustained reasoning,
arXiv:2609.38415v1 Announce Type: cross Abstract: This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI syste
arXiv:2609.38406v1 Announce Type: new Abstract: Access to real-world information is often noisy and fragmented. Constructing a coherent narrative from such fragments requires models to reconstruct mis
arXiv:2609.40230v1 Announce Type: cross Abstract: Visual perception is conventionally formulated as a one-shot prediction from a single glance at the image, under the assumption that the image content
arXiv:2609.40340v1 Announce Type: new Abstract: Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents
Excited to share that I have joined @MistralAI, where I will be building a team in Montreal and across Canada to push the frontier of safe, capable, and open LLMs. Mistral has played, and will continu
arXiv:2606.13571v2 Announce Type: replace-cross Abstract: Real-world time series are often highly incomplete and irregular due to sensor dormancy, transmission delays, and event-driven sampling, makin
arXiv:2609.39624v1 Announce Type: new Abstract: Single-image HDR reconstruction requires inferring missing detail while preserving the visible content of an LDR image. Differences in sensor dynamic ra
arXiv:2609.39786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based K
arXiv:2609.39369v1 Announce Type: new Abstract: Specialized models encode task-oriented behavior, but transferring that behavior to a general language model usually requires training, distillation, or
arXiv:2609.39279v1 Announce Type: cross Abstract: Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety alignment in Large Language Models (LLMs).
arXiv:2609.39649v1 Announce Type: new Abstract: Video super-resolution (VSR) is normally judged by PSNR and SSIM on clips that were downsampled bicubically, although in surveillance its purpose is to
arXiv:2609.39748v1 Announce Type: new Abstract: Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains undere
arXiv:2511.10796v2 Announce Type: replace-cross Abstract: The empirical state-space Neural Tangent Kernel (NTK) describes the local learning geometry of a finite-width neural network, but computing it
arXiv:2406.02447v5 Announce Type: replace Abstract: Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguar
arXiv:2609.38897v1 Announce Type: cross Abstract: Far-field automatic speech recognition(ASR) degrades under reverberation, noise, and talker motion, yet the benchmarks that drive model selection emph
arXiv:2609.38216v1 Announce Type: new Abstract: Existing benchmarks evaluate tabletop manipulation, flat-floor household activity, or humanoid locomotion and manipulation as separate task groups; none
arXiv:2609.39184v1 Announce Type: new Abstract: Fiber orientation and compartmental microstructure are central to the characterization of white matter tissue in diffusion MRI, yet existing methods eit
I was waiting on the blowers for the T4s and posted this before it was finished, other than some braided cable sleeves for the fan wires its pretty much good, I was going to upgrade the CPU, but I'm g
NVIDIA Nemotron 3.5 ASR was fine‑tuned on 133.7 h of Saudi Najdi and Hijazi speech using weighted replay with FLEURS data, duration bucketing, and selective encoder unfreezing; this reduced the target
arXiv:2609.38719v1 Announce Type: new Abstract: Experimental investigation and modeling of flapping-wing aerial vehicles are limited by the scarcity of large-scale records that temporally align wing k
arXiv:2609.38585v1 Announce Type: cross Abstract: Existing Large Language Model (LLM) routing methods score LLMs independently to select top-k models. However, this ignores model correlations and enfo
arXiv:2609.38251v1 Announce Type: cross Abstract: The rapid evolution of image manipulation techniques has raised growing public security concerns. Existing Image Forgery Localization (IFL) methods ca
arXiv:2609.39634v1 Announce Type: cross Abstract: Common policy improvement methods, including TRPO, PPO, and GRPO, estimate policy improvement under the behavioral policy's state-visitation distribut
I've run the benchmark on a RTX 3090, 1024 tokens in / 256 out, concurrency 1–32. If the model fits on vRAM (Gemma-4-26B-A4B, byte-identical GGUF on both engines): llama.cpp has 2.2–3.2× the throughpu
arXiv:2510.17932v5 Announce Type: replace-cross Abstract: We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (L
arXiv:2511.22232v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly capable in medical imaging, yet most focus on single-image settings. Clinical interp