Knowledge catalogue
arXiv:2606.06423v1 Announce Type: new Abstract: Safety-critical traffic scenario generation is essential for evaluating autonomous driving systems under rare but high-risk interactions. Existing diffu
arXiv:2606.06188v1 Announce Type: new Abstract: Recent work has sought to understand Large Language Models (LLMs) reasoning, yet a principled, model-intrinsic signal that captures its layer-wise reaso
arXiv:2606.06476v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have shown strong visual reasoning capabilities, their spatial reasoning abilities remain largely constrained to the
Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for agents! The popular theory goes: agents can write code, so they'll just rebuild every tool from scratc
arXiv:2601.21700v3 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining dat
arXiv:2602.03410v2 Announce Type: replace Abstract: Recent advances in large-scale diffusion models have intensified concerns about their potential misuse, particularly in generating realistic yet har
arXiv:2606.05688v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models scale foundation models efficiently by activating only a subset of experts for each token, but their large number of exp
arXiv:2606.06369v1 Announce Type: new Abstract: Learning-driven Scene Graph Generation (SGG) models excel on frequent relation types but degrade sharply under annotation sparsity, failing to capture r
arXiv:2606.05414v1 Announce Type: new Abstract: Early failure alerting requires deciding, while a dialog or agent trajectory is still unfolding, whether to flag it as likely to fail. This is challengi
arXiv:2606.05868v1 Announce Type: new Abstract: Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory
arXiv:2510.24342v2 Announce Type: replace Abstract: Prior brain-AI alignment studies are typically constrained by specific inputs and tasks, limiting their ability to capture organizational properties
arXiv:2606.04775v1 Announce Type: cross Abstract: Text-to-video (T2V) models trained on large-scale web data can generate undesired content, motivating interventions that reduce harmful outputs withou
arXiv:2606.04874v1 Announce Type: new Abstract: Planning is central to LLM agents: before acting, an agent must decompose goals, select tools, reason over constraints, and decide when a task is infeas
arXiv:2606.05149v1 Announce Type: new Abstract: Vehicle body type is a significant determinant of cyclist injury severity in overtaking crashes, yet automated tools for classifying vehicles into injur
arXiv:2606.05035v1 Announce Type: new Abstract: Long-horizon online visual mapping is a core capability for robot perception, requiring continuous camera-motion and scene-geometry estimation from visu
arXiv:2606.05121v1 Announce Type: cross Abstract: Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only
B9500 is a release of llama.cpp that includes a Metal backend optimization reducing reset heartbeat timing from 500ms to 5ms . The release provides compiled binaries across multiple platforms includin
arXiv:2606.04845v1 Announce Type: cross Abstract: Sequential decision-making problems are often modelled as a Markov decision process (MDP). We focus on the stochastic shortest path (SSP) problem, whi
arXiv:2606.04494v1 Announce Type: new Abstract: Biomedical agents promise to automate complex biological workflows, yet current systems face two fundamental bottlenecks: bioinformatics tools are highl
arXiv:2603.23420v2 Announce Type: replace Abstract: If autoresearch is itself a form of research, then autoresearch can be applied to research itself. We present Bilevel Autoresearch, a bilevel framew
arXiv:2209.15448v3 Announce Type: replace Abstract: As AI becomes more prevalent throughout society, effective methods of integrating humans and AI systems that leverage their respective strengths and
arXiv:2510.17064v4 Announce Type: replace Abstract: Single-cell RNA sequencing has transformed our ability to identify diverse cell types and their transcriptomic signatures. However, annotating these
arXiv:2606.04072v1 Announce Type: cross Abstract: Deep learning models are increasingly central to autonomous vehicle (AV) pipelines, yet their integration has traditionally followed a monolithic desi
arXiv:2510.08647v2 Announce Type: replace-cross Abstract: Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during
arXiv:2606.04461v1 Announce Type: new Abstract: Leading flexible vision tokenizers achieve SOTA quality at an extreme cost, relying on parameter-heavy backbones and slow, multi-step generative decoder
arXiv:2606.04130v1 Announce Type: new Abstract: We introduce CLAW, a fully end-to-end self-supervised framework for learning a world model jointly with continuous latent action representations directl
arXiv:2606.04418v1 Announce Type: cross Abstract: Neural audio codecs are a key component of speech processing pipelines, compressing audio into discrete tokens for downstream modeling. However, exist
arXiv:2606.04071v1 Announce Type: cross Abstract: As language models increasingly consume one another's outputs, covert influence -- a phenomenon where a sender's payload (the behavioral disposition i
arXiv:2606.04884v1 Announce Type: new Abstract: Traditional end-to-end autonomous driving frameworks frequently suffer from the 'style-averaging' dilemma when trained on high-variance human demonstrat
arXiv:2606.04710v1 Announce Type: new Abstract: This work presents a data-efficient variant of the Attention-Based Dual-Branch Complex Feature Fusion Network (CFFN) for hyperspectral image classificat
arXiv:2511.01192v2 Announce Type: replace Abstract: Detecting machine-generated text has become a critical challenge amid the rapid advancement of LLMs, yet existing detectors degrade severely under d
arXiv:2606.04360v1 Announce Type: new Abstract: Symbolic regression (SR) discovers compact mathematical expressions from data, yet recent LLM-based evolutionary methods remain sample-inefficient becau
arXiv:2503.18721v3 Announce Type: replace-cross Abstract: Identification of joint dependence among several random vectors plays an important role in many statistical applications, where the data may c
arXiv:2606.04881v1 Announce Type: cross Abstract: Face aging plays an important role in long-term biometric analysis, cross-age identity verification, and forensic identity analysis. Since the same su
arXiv:2606.04844v1 Announce Type: cross Abstract: Contrastive audio-language models such as CLAP enable zero-shot audio classification: a sound is labelled by matching its embedding to text prompt emb
arXiv:2512.16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-tar
arXiv:2512.03553v3 Announce Type: replace-cross Abstract: Content moderation remains a critical yet challenging task for large-scale user-generated video platforms, especially in livestreaming environ
arXiv:2502.03799v4 Announce Type: replace Abstract: Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations. Effectively detecting hallucination
arXiv:2606.04705v1 Announce Type: cross Abstract: Semantic segmentation in medical imaging is a critical yet challenging task due to data scarcity and high variability across modalities. While foundat
arXiv:2606.04160v1 Announce Type: new Abstract: Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed r
arXiv:2606.05145v1 Announce Type: cross Abstract: When post-trained language models fail on reasoning problems, the common test-time-scaling response is to spend more compute on additional attempts, a
arXiv:2606.04591v1 Announce Type: new Abstract: With the widespread adoption of multi-modal communication platforms, long-form dialogues interleaving text and images have become increasingly common. U
arXiv:2606.04307v1 Announce Type: new Abstract: Bayesian models with finite symmetry - mixture models with exchangeable components, structural identification with closely-spaced modes - define posteri
arXiv:2606.04381v1 Announce Type: cross Abstract: Recent large language models (LLMs) often appear to exhibit spatial reasoning ability; however, this capability is largely symbolic, arising from patt
arXiv:2606.04889v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (e.g. GRPO) is now a common way to improve mathematical reasoning in Large Language Models (LLMs). Howeve
arXiv:2606.05030v1 Announce Type: new Abstract: Autoregressive chain-of-thought (CoT) reasoning in large language models (LLMs) is fundamentally forward-directed: each step conditions only on prior to
arXiv:2606.04656v1 Announce Type: cross Abstract: Object detection is a safety-critical component of autonomous driving. It is essential to quantify the uncertainty in bounding-box predictions for saf
arXiv:2606.04269v1 Announce Type: cross Abstract: Deformable object manipulation (DOM) is challenging due to high-dimensional, partially observable states that evolve through long-horizon, topology-ch
Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise work
arXiv:2601.21461v3 Announce Type: replace-cross Abstract: Modern sparse language models typically achieve sparsity through Mixture-of-Experts (MoE) layers, which dynamically route tokens to dense MLP
arXiv:2606.04597v1 Announce Type: new Abstract: Admissible heuristics are essential for optimal planning, yet learning them remains challenging due to the risk of overestimation. Cost partitioning com
arXiv:2606.05073v1 Announce Type: new Abstract: Missing value imputation is a fundamental task in machine learning, with most existing methods assuming that all missing entries correspond to unobserve
arXiv:2603.03205v2 Announce Type: replace Abstract: Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon ac
arXiv:2606.04815v1 Announce Type: cross Abstract: Lifelong learning is essential for Large Language Model (LLM) agents operating in dynamic, interactive environments. However, existing lifelong learni
arXiv:2606.04063v1 Announce Type: cross Abstract: Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements. While some methods address this
arXiv:2606.04534v1 Announce Type: new Abstract: Agile quadrotor flight in cluttered scenes requires more than a reactive mapping from a depth image to a control command: the vehicle must remember whic
arXiv:2606.04880v1 Announce Type: new Abstract: Selection is a core operation in interactive image editing. To be practical, a user should be able to specify and disambiguate the desired selection reg
arXiv:2511.00801v4 Announce Type: replace Abstract: Text-guided medical image editing must satisfy the requested pathology while preserving anatomy, modality-specific appearance, and clinical plausibi
arXiv:2511.07107v3 Announce Type: replace Abstract: Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address im
arXiv:2606.04621v1 Announce Type: new Abstract: We present MeshFlow, a new method for generating artist-like 3D meshes. Current mesh generators often adopt Auto-Regressive (AR) next-token prediction,