Knowledge catalogue
arXiv:2604.25255v1 Announce Type: new Abstract: Speech-preserving facial expression manipulation (SPFEM) aims to enhance human expressiveness without altering mouth movements tied to the original spee
arXiv:2511.03125v2 Announce Type: replace-cross Abstract: We study how to accelerate Bayesian optimization (BO) on a target task by transferring historical knowledge from related source tasks. Existin
The classroom changed. The homework changed. How we learn changed. 18 million students already build on Replit and now, there's a dedicated space just for them. No setup. No lectures. Just building. T
arXiv:2604.25530v1 Announce Type: new Abstract: Recent knowledge distillation (KD) methods for semantic segmentation introduce increasingly complex hand-crafted objectives, yet are typically evaluated
arXiv:2604.25208v1 Announce Type: new Abstract: Radiometric inconsistencies remain a major challenge in generating seamless lunar mosaics from multi-mission orbital imagery due to variability in illum
arXiv:2511.14183v3 Announce Type: replace Abstract: Digital images are often degraded by soft effects such as lens flare, haze, shadows, and reflections, which reduce aesthetics even though the underl
arXiv:2604.24953v1 Announce Type: new Abstract: While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Curr
arXiv:2604.22830v1 Announce Type: new Abstract: Pre-training is a general method that is used in a range of deep learning tasks. By first training a model on one task, and then further training on the
A few notes on how to get started with building LLM Knowledge Bases. @karpathy popularized it but most people don't know where to start. Everyone should be creating LLM Wikis. Live session tomorrow. S
arXiv:2604.23790v1 Announce Type: new Abstract: A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle
arXiv:2510.18346v2 Announce Type: replace Abstract: Audio-Visual Question Answering (AVQA) requires models to effectively utilize both visual and auditory modalities to answer complex and diverse ques
arXiv:2602.02556v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on extern
arXiv:2604.22759v1 Announce Type: cross Abstract: In community question answering (cQA) platforms like Stack Overflow, related question retrieval is recognized as a fundamental task that allows users
arXiv:2604.23249v1 Announce Type: new Abstract: Learning robot manipulation from human videos is appealing due to the scale and diversity of human demonstrations, but transferring such demonstrations
arXiv:2604.24201v1 Announce Type: new Abstract: Motivation: Multi-omics integration can improve cancer subtyping, but modality informativeness and noise vary across cancer types and patients. Existing
arXiv:2604.22812v1 Announce Type: cross Abstract: STEM dropout rates remain high at universities, particularly in computer science programs with theory-intensive courses. Digital learning environments
arXiv:2604.23874v1 Announce Type: cross Abstract: Deep learning approaches have shown remarkable promise in turbulence closure modeling for large eddy simulations (LES). The differentiable physics par
arXiv:2510.13087v3 Announce Type: replace Abstract: Marketing Mix Modeling (MMM) estimates the impact of marketing activities on business outcomes such as sales or revenue. Traditional MMM approaches
arXiv:2506.21107v3 Announce Type: replace Abstract: Estimating single-cell responses across various perturbations facilitates the identification of key genes and enhances drug screening, significantly
arXiv:2406.05984v2 Announce Type: replace-cross Abstract: Mental health constitutes a complex and pervasive global challenge, affecting millions of lives and often leading to severe consequences. In t
arXiv:2604.23354v1 Announce Type: cross Abstract: Neural networks can be trained to learn task-relevant representations from data. Understanding how these networks make decisions falls within the Expl
arXiv:2504.10527v2 Announce Type: replace Abstract: Artificial Intelligence (AI) has become essential for analyzing complex data and solving highly-challenging tasks. It is being applied across numero
arXiv:2604.23267v1 Announce Type: new Abstract: Large language models (LLMs) operate in two fundamental learning modes - fine-tuning (FT) and in-context learning (ICL) - raising key questions about wh
arXiv:2604.23194v1 Announce Type: new Abstract: Large language model-based agents have recently emerged as powerful approaches for solving dynamic and multi-step tasks. Most existing agents employ pla
// From Skill Text to Skill Structure // One of the more practical skill papers I've seen this month. SKILL.md files entangle invocation interface, execution flow, and tool/resource side effects in on
arXiv:2512.00127v3 Announce Type: replace-cross Abstract: Getting language models to reason correctly about code requires training on data where each reasoning step can be checked. Current synthetic C
arXiv:2604.23912v1 Announce Type: new Abstract: Learning low-dimensional representations from multi-view relational data is challenging when underlying geometries differ across views. We propose Bary-
This post from Cristobal Valenzuela, a notable AI researcher and co-founder of Runway ML, uses the colloquial phrase 'He is a goat' (an acronym meaning 'Greatest Of All Time') to express acclaim for s
However, older versions have a critical CVE, so you do need to upgrade! If you use uv (thanks to @charliermarsh) you can pop this in your pyproject to work around it: ``` [tool.uv] override-dependenci
I know the litellm team have a *lot* going on, & I have no desire to increase their workload even more… But if you're a litellm user, this is a critical issue to know about - it currently force downgr
arXiv:2602.01386v2 Announce Type: replace-cross Abstract: Generative AI (GenAI) tools are rapidly transforming knowledge work, making AI literacy a critical priority for organizations. However, resear
I'm speechless at Google signing a deal to use our AI models for classified tasks. Frankly, it is shameful. For HR, I'm not speaking on behalf of Google but in my personal capacity, quoting public inf
arXiv:2604.24662v1 Announce Type: cross Abstract: Identifying the dynamical state variables of a system from high-dimensional observations is a central problem across physical sciences. The challenge
arXiv:2604.23865v1 Announce Type: cross Abstract: Foundation models of brain activity promise a new frontier for in silico neuroscience by emulating neural responses to complex stimuli across tasks an
arXiv:2509.20237v2 Announce Type: replace Abstract: Backchannels and fillers are important linguistic expressions in dialogue, but often treated as 'noise' to be bypassed in modern transformer-based l
This resource explains techniques for creating videos with consistent characters and voices in Runway, likely covering the use of reference materials, character sheets, and specific prompting strategi
arXiv:2604.23403v1 Announce Type: cross Abstract: This paper proposes a new method to improve the training efficiency of deep convolutional neural networks. During training, the method evaluates score
arXiv:2508.19068v2 Announce Type: replace Abstract: Single-Pixel Imaging (SPI) enables the reconstruction of objects using a single detector through sequential illuminations with structured light patt
arXiv:2503.20066v2 Announce Type: replace-cross Abstract: Dense reconstruction and differentiable rendering are fundamental tightly connected operations in 3D vision and computer graphics. Recent neur
arXiv:2604.24608v1 Announce Type: cross Abstract: Large Language Models (LLMs) have recently been explored as fine-grained zero-shot re-rankers by leveraging attention signals to estimate document rel
arXiv:2604.24737v1 Announce Type: cross Abstract: We study learning with Chain-of-Thought (CoT) supervision from multiple thinkers, all of whom provide correct but possibly systematically different so
Conditional diffusion models appear capable of compositional generalization, i.e., generating convincing samples for out-of-distribution combinations of conditioners, but the mechanisms underlying thi
arXiv:2604.22848v1 Announce Type: new Abstract: Recent times have seen an increase in demand of high quality Digital Elevation Models (DEMs) for the lunar surface, because they are highly important fo
arXiv:2604.22854v1 Announce Type: cross Abstract: Transformer architectures, including nnFormer,have demonstrated promising results in volumetric medical image segmentation by being able to capture lo
arXiv:2604.24332v1 Announce Type: new Abstract: Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representatio
arXiv:2412.07160v3 Announce Type: replace Abstract: To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts
arXiv:2407.14974v2 Announce Type: replace-cross Abstract: Machine learning models are known to learn spurious correlations, i.e., features having strong relations with class labels but no causal relat
arXiv:2604.24167v1 Announce Type: new Abstract: Implicit neural representations (INRs) are increasingly being used as tools to map coordinates to signals, encompassing applications from neural fields
arXiv:2604.24586v1 Announce Type: new Abstract: Single-image point cloud reconstruction must infer complete 3D geometry, including occluded parts, from a single RGB image. While diffusion-based recons
arXiv:2604.22868v1 Announce Type: cross Abstract: Visual planning represents a crucial facet of human intelligence, especially in tasks that require complex spatial reasoning and navigation. Yet, in m
arXiv:2604.23974v1 Announce Type: new Abstract: Fake news generally refers to false information that is spread deliberately to deceive people, which has detrimental social effects. Existing fake news
arXiv:2510.11541v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge so
arXiv:2604.04353v2 Announce Type: replace-cross Abstract: Although HCI research papers offer valuable design insights, designers often struggle to apply them in design workflows due to difficulties in
arXiv:2604.23842v1 Announce Type: cross Abstract: Neologisms and emerging slang are central to daily conversation, yet challenging for non-native speakers (NNS) to interpret and use appropriately in c
arXiv:2604.23985v1 Announce Type: new Abstract: In autoregressive large language models (LLMs), temporal straightening offers an account of how the next-token prediction objective shapes representatio
arXiv:2604.24036v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have enhanced grounding capabilities in general scenes, their robustness in crowded scenes remains undere
arXiv:2512.20562v2 Announce Type: replace-cross Abstract: We study the problem of learning a low-degree spherical polynomial of degree ell_0 = Theta(1) ge 1 defined on the unit sphere in RR^d by train
Should we care about AI happiness? In our new research, we find evidence of functional AI wellbeing across several independent measures. We find which AI models are happiest, how to make them happier,
arXiv:2604.23996v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert
arXiv:2401.07669v2 Announce Type: replace Abstract: Adapting CLIP for videos has gained popularity due to its semantic and rich representation. While CLIP is a good starting point, it typically underg