Knowledge catalogue
arXiv:2608.00078v1 Announce Type: new Abstract: Deploying convolutional neural networks generated by large language models (LLMs) on real mobile hardware requires more than GPU validation accuracy: IN
arXiv:2608.01985v1 Announce Type: new Abstract: Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. The key is to learn a score th
arXiv:2608.01816v1 Announce Type: new Abstract: In this work we investigate how decoder-only transformers resolve lexical ambiguity through layer-by-layer analysis of three models spanning three param
arXiv:2608.00086v1 Announce Type: new Abstract: Brain tumor diagnosis is a time-sensitive process in which patients may wait weeks for a finalized pathology report. This problem motivates automated sy
early sparks of rsi? Ali Taha @waterloo_intern explains how http://Z.ai's GLM-5.2 (@Zai_org) profiled its SGLang serving path and rewrote bottlenecked GPU kernels, (still lacks reliable judgment) grea
arXiv:2510.01925v3 Announce Type: replace Abstract: Reward models (RMs) play a critical role in enhancing the reasoning performance of LLMs. For example, they can provide training signals to finetune
arXiv:2608.02284v1 Announce Type: new Abstract: Open-vocabulary segmentation identifies and segments objects from arbitrary textual descriptions. SAM 3 supports noun-phrase-guided segmentation and ach
arXiv:2603.03320v2 Announce Type: replace Abstract: Effective communication often relies on aligning a message with an audience's narrative and worldview. Narrative shift involves transforming text to
arXiv:2608.01737v1 Announce Type: new Abstract: As digital drawings are increasingly shared online, reliable authorship verification has become important for protecting artists and resolving disputes.
arXiv:2608.00490v1 Announce Type: new Abstract: Can image-editing models discover visual rules in image space and complete problem-solving end-to-end? We tackle this question in the spirit of a human
arXiv:2608.00237v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs
arXiv:2603.10648v3 Announce Type: replace Abstract: Current skeleton representation learning paradigms face distinct limitations: Contrastive Learning (CL) often overlooks fine-grained motion details,
arXiv:2608.01635v1 Announce Type: new Abstract: Despite the progress of multimodal large language models (MLLMs), they continue to exhibit deficiencies in visual perception. Following visual instructi
arXiv:2604.02817v2 Announce Type: replace Abstract: Despite advancements in generating visually stunning content, video diffusion models (VDMs) often yield physically inconsistent results due to pixel
arXiv:2608.01153v1 Announce Type: new Abstract: Statistical subword tokenizers can process arbitrary text, but their units need not align with lexical or grammatical structure. This is especially impo
arXiv:2409.03901v4 Announce Type: replace Abstract: Remote sensing (RS) image classification is central to Earth observation, but onboard deployment requires models that are accurate, efficient, and r
arXiv:2607.17082v2 Announce Type: replace-cross Abstract: Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results. Current eva
arXiv:2608.01825v1 Announce Type: new Abstract: Part-level 3D generation has recently attracted increasing attention for producing structured and editable 3D assets. However, existing methods typicall
arXiv:2601.02457v2 Announce Type: replace Abstract: Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent
arXiv:2608.01978v1 Announce Type: new Abstract: Audio-driven portrait animation has advanced rapidly with diffusion-based generative models, yet real-time one-shot generation with expressive emotion c
arXiv:2608.00508v1 Announce Type: new Abstract: Object detection and segmentation in three-dimensional medical images is a very active area of research. However, most proposed deep learning models car
arXiv:2608.01506v1 Announce Type: cross Abstract: Humans readily adapt their movements as their bodies change through aging, injury, or load carrying, but learning-based robot policies often break whe
arXiv:2608.00444v1 Announce Type: new Abstract: Unsupervised medical anomaly detection learns normal anatomical patterns from healthy training images and identifies deviations at test time. Reconstruc
arXiv:2608.00503v1 Announce Type: cross Abstract: Predictive coding offers a powerful framework for cortical computation, yet scalable implementations that respect both Bayesian exactness and neurobio
arXiv:2511.11686v4 Announce Type: replace Abstract: Speech enhancement (SE) requires high-fidelity reconstruction of clean speech that preserves linguistic and paralinguistic cues while maintaining hi
Remember OpenAI tripled its score on ARC-AGI with a harness fix? We fixed harness for Kimi K3 on CyberGym E2E: 2x better at vulnerability detection, 3x at patching K3 is SOTA cyber-defense model you c
arXiv:2608.01271v1 Announce Type: new Abstract: Video large language models (Video-LLMs) represent videos as dense sequences of visual tokens, whose length grows with the temporal and spatial extent o
arXiv:2608.00725v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future observations. However, conditioning future prediction on
arXiv:2608.02290v1 Announce Type: new Abstract: ANN-based All-in-One image restoration (AiOIR) unifies diverse degradation handling but incurs high computational costs, limiting its real-time deployme
arXiv:2608.02050v1 Announce Type: new Abstract: Can a strictly local, iterated, weight-shared computation primitive support language modelling, and which of those three properties actually drives the
arXiv:2608.00492v1 Announce Type: cross Abstract: Predictive coding offers a powerful theory of cortical computation, but corresponding scalable algorithmic implementations for artificial intelligence
arXiv:2608.01724v1 Announce Type: new Abstract: Group conversations are fundamental to human collaboration, yet standard large language models (LLMs) still struggle with the complexities of multi-part
arXiv:2608.00200v1 Announce Type: cross Abstract: Wearable sensors capture fine-grained motion patterns that support rich behavioral understanding, yet most existing methods reduce these signals to ac
arXiv:2603.17445v5 Announce Type: replace-cross Abstract: When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable?
arXiv:2607.29456v1 Announce Type: cross Abstract: Double Machine Learning (DML) is a popular approach for treatment effect estimation in various settings, which allows a wide range of flexible machine
arXiv:2607.28966v1 Announce Type: new Abstract: Large language models often improve task performance by generating long reasoning traces, but the resulting computation is frequently wasted on redundan
arXiv:2607.22186v2 Announce Type: replace Abstract: Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimiza
arXiv:2607.29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases. As a
arXiv:2607.28788v1 Announce Type: new Abstract: Clinical diagnosis at hospital admission must be made rapidly from limited, incomplete evidence. Existing diagnosis-prediction benchmarks are poorly sui
arXiv:2512.17303v2 Announce Type: replace Abstract: In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free gui
arXiv:2607.28659v1 Announce Type: new Abstract: Cross-domain sequential recommendation (CDSR) aims to model users' dynamic interest transitions and sequential patterns across multiple domains. Recentl
arXiv:2607.29037v1 Announce Type: new Abstract: Active 3D reconstruction relies on active view selection to maximize reconstruction fidelity under limited capture budgets. However, most existing metho
arXiv:2607.29144v1 Announce Type: cross Abstract: Synthetic face datasets are increasingly used to reduce privacy exposure and data access constraints in biometric recognition. Yet the generators that
I have been working on this tool for months and there are a lot of new functionalities and tests that are going to be released in the next few weeks! The goal of the tool is to allow community members
arXiv:2607.29185v1 Announce Type: new Abstract: Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs ena
arXiv:2607.29559v1 Announce Type: new Abstract: Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tas
arXiv:2607.29192v1 Announce Type: new Abstract: Remote sensing scene classification is increasingly relying on foundation models pre-trained on large-scale Earth-observation data. Moreover, transducti
Tim Bradshaw / Financial Times: London-based AI chip startup Olix raised 312M led by Fundomo, with participation from Arm, at a 3.3B valuation, up from 1B+ after raising 220M in February — British ent
arXiv:2607.28645v1 Announce Type: cross Abstract: Recent multimodal large language models can convert visual designs directly into executable code, but real mobile products require multiple screenshot
arXiv:2607.28629v1 Announce Type: new Abstract: The rapid transition from reactive large language models (LLMs) to persistent, action-capable systems has exposed critical gaps in the architectural und
arXiv:2512.12816v2 Announce Type: replace Abstract: We study how to allocate resources for training and deployment of machine learning (ML) models under concept drift and limited budgets. We consider
arXiv:2607.29606v1 Announce Type: cross Abstract: A fundamental challenge of vector search is achieving consistently high recall while minimizing computational costs. Fixed search parameters cause sig
arXiv:2602.07339v2 Announce Type: replace Abstract: Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck fo
arXiv:2507.22580v2 Announce Type: replace-cross Abstract: Automated Program Repair (APR) seeks to automatically correct software bugs without requiring human intervention. However, existing tools tend
arXiv:2607.28759v1 Announce Type: cross Abstract: In X-ray CT, metallic objects cause beam hardening, photon starvation, and scattering, leading to projection inconsistency, streaks, dark bands, and s
arXiv:2607.29468v1 Announce Type: new Abstract: Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gra
arXiv:2603.06274v2 Announce Type: replace-cross Abstract: The quadratic computational complexity of self-attention remains a fundamental bottleneck for scaling Large Language Models (LLMs) to long con
arXiv:2607.29482v1 Announce Type: new Abstract: By relying on independent couplings from uninformative Gaussian priors, standard diffusion and flow matching models are forced to learn complex, high-co
arXiv:2607.28643v1 Announce Type: cross Abstract: Automating facilitation in online discussions is a long-standing social concern given the increasing time we spend on online spaces and the failure of
arXiv:2603.09161v2 Announce Type: replace-cross Abstract: Learning effective netlist representations is fundamentally constrained by the scarcity of labeled datasets, as real designs are protected by