Knowledge catalogue
arXiv:2601.22904v2 Announce Type: replace-cross Abstract: Recent studies have explored using pretrained Vision Foundation Models (VFMs) such as DINO for generative autoencoders, showing strong generat
arXiv:2601.22143v2 Announce Type: replace-cross Abstract: Audio-Visual Foundation Models, which are pretrained to jointly generate sound and visual content, have recently shown an unprecedented abilit
arXiv:2605.08209v1 Announce Type: new Abstract: Deep learning methods are widely used under diverse resource constraints, resulting in models of varying sizes, such as the Vision Transformer (ViT) ser
arXiv:2605.08557v1 Announce Type: cross Abstract: Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight resi
arXiv:2510.09887v2 Announce Type: replace Abstract: Vision and language models frequently ignore semantically critical input edits, defaulting to pretraining priors. For example, models will confident
arXiv:2605.08800v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmar
arXiv:2605.09189v1 Announce Type: new Abstract: The scaling laws guiding modern model training were calibrated for a single regime: data-rich, single-epoch pretraining. The dominant such scaling law f
arXiv:2605.10385v1 Announce Type: cross Abstract: Guided-diffusion black-box optimization (BO) has shown strong empirical performance on structured design problems such as molecules and crystals, but
arXiv:2605.08589v1 Announce Type: new Abstract: Parameter Efficient Fine-Tuning (PEFT) is a key technique for adapting a large pretrained model to downstream tasks by fine-tuning only a small number o
arXiv:2605.09989v1 Announce Type: cross Abstract: Recent advances in robot imitation learning have yielded powerful visuomotor policies capable of manipulating a wide variety of objects directly from
arXiv:2605.10734v1 Announce Type: new Abstract: For reinforcement learning in the real world online exploration is expensive A common practice in robotic reinforcement learning is to incorporate addit
arXiv:2602.19612v3 Announce Type: replace Abstract: Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts
arXiv:2509.21637v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning (PEFT) of large language models trains a small task-specific parameter set while keeping the pretrained model frozen
arXiv:2605.07040v1 Announce Type: cross Abstract: Large language models (LLMs) are widely used for tutoring, feedback generation, and content creation, but their broad pretraining makes them hard to c
arXiv:2511.18085v4 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models show promising knowledge accumulation ability from pretraining, yet continual learning in VLA remains chal
arXiv:2605.06885v1 Announce Type: cross Abstract: Diffusion language models (DLMs) have recently demonstrated capabilities that complement standard autoregressive (AR) models, particularly in non-sequ
arXiv:2605.07075v1 Announce Type: new Abstract: The open-source model ecosystem now contains hundreds of thousands of pretrained models, yet picking the best model for a new dataset is increasingly in
arXiv:2503.14998v3 Announce Type: replace Abstract: Contrastive learning methods in computer vision typically rely on augmented views of the same image or multimodal pretraining strategies that align
arXiv:2602.02739v2 Announce Type: replace-cross Abstract: Geometric data pruning methods, while practical for leveraging pretrained models, are fundamentally unstable. Their reliance on extrinsic geom
arXiv:2605.06990v1 Announce Type: new Abstract: Multimodal self-supervised learning (MSSL) has emerged as a key paradigm for pretraining geospatial foundation models. However, existing geospatial MSSL
arXiv:2511.03182v2 Announce Type: replace-cross Abstract: Large language models (LLMs) for code are increasingly used in software development, but they remain static after pretraining while APIs and s
The Top AI Papers of the Week (May 4 - 10) - Conductor - HeavySkill - Horizon Generalization - 1,000 Synthetic Computers - Self-Improving Pretraining - Coordination as Architecture - Connect Four Alph
arXiv:2605.03871v1 Announce Type: new Abstract: Language models encode substantial evaluative knowledge from pretraining, yet current post-training methods rely on external supervision (human annotati
arXiv:2605.05197v1 Announce Type: new Abstract: Grammaticality and likelihood are distinct notions in human language. Pretrained language models (LMs), which are probabilistic models of language fitte
Technical highlights: CogViT Vision Encoder - Built with dual-teacher distillation: SigLIP2 for semantics, DINOv3 for texture. A two-stage recipe, masked modeling, then contrastive pretraining, with Q
arXiv:2504.17816v3 Announce Type: replace Abstract: Subject-driven video generation (SDV-Gen) aims to produce videos of a specific subject by adapting a pretrained video model, enabling personalized a
arXiv:2605.03866v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) models excel at understanding image-text relationships but struggle with adapting to new data without forg
arXiv:2605.03359v1 Announce Type: new Abstract: Recent trends in sparse-view 3D reconstruction have taken two different paths: feed-forward reconstruction that predicts pixel-aligned point maps withou
arXiv:2605.03229v1 Announce Type: new Abstract: Adapting a pretrained language model to a new task often hurts the general capabilities it already had, a problem known as catastrophic forgetting. Spar
arXiv:2605.00899v1 Announce Type: new Abstract: We present LatentDiff, a scalable framework for semantic dataset comparison that operates directly in the latent space of pretrained vision encoders. By
arXiv:2510.23633v2 Announce Type: replace-cross Abstract: Pretrained diffusion models have demonstrated strong capabilities in zero-shot inverse problem solving by incorporating observation informatio
arXiv:2605.00973v1 Announce Type: new Abstract: Biosignals acquired from different locations on the body often provide temporally ordered views of the same underlying physiological process. However, m
arXiv:2605.01364v1 Announce Type: new Abstract: The building energy community lacks a foundational thermal model, i.e., a single pretrained model capable of generalizing across diverse buildings, clim
arXiv:2510.19897v2 Announce Type: replace Abstract: We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without p
arXiv:2602.18196v3 Announce Type: replace Abstract: Structured dilated attention has an appealing inference-time efficiency knob: it reduces the FLOPs of attention and the KV cache size by a factor of
arXiv:2605.00401v1 Announce Type: new Abstract: Recent EEG-to-image retrieval methods leverage pretrained vision encoders and foveation-inspired priors, but typically assume a fixed, center-focused vi
arXiv:2605.00015v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TS
arXiv:2509.24255v2 Announce Type: replace-cross Abstract: As virtual reality (VR) becomes widespread, head and hand motion data captured by consumer systems has become substantially more common. Howev
arXiv:2604.04306v2 Announce Type: replace-cross Abstract: The increasing frequency and severity of climate related disasters have intensified the need for real time monitoring, early warning, and info
arXiv:2604.26498v1 Announce Type: new Abstract: The rapid growth of molecular foundation models and general-purpose large language models has encouraged a scale-centric view of artificial intelligence
arXiv:2601.03423v3 Announce Type: replace-cross Abstract: Adapting language models to the clinical domain through continued pretraining and instruction tuning requires costly retraining for each new m
arXiv:2604.26694v1 Announce Type: cross Abstract: We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruc
arXiv:2604.25427v1 Announce Type: new Abstract: While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a signif
arXiv:2604.25599v1 Announce Type: cross Abstract: Code understanding models increasingly rely on pretrained language models (PLMs) and graph neural networks (GNNs), which capture complementary semanti
arXiv:2604.22794v1 Announce Type: cross Abstract: Reinforcement learning (RL) offers a promising approach for adaptive wind farm flow control, yet its practical deployment is hindered by slow training
arXiv:2604.24136v1 Announce Type: new Abstract: Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR) but suffer from computational bottlenecks due to iterative
arXiv:2601.18399v2 Announce Type: replace Abstract: Separating liquid-liquid dispersions in gravity settlers is critical in chemical, pharmaceutical, and recycling processes. The dense-packed zone hei
arXiv:2604.23452v1 Announce Type: new Abstract: Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supe
arXiv:2510.14978v2 Announce Type: replace Abstract: Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine
arXiv:2604.00829v3 Announce Type: replace-cross Abstract: Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representat
arXiv:2604.23720v1 Announce Type: new Abstract: Metanetworks are neural architectures designed to operate directly on pretrained weights to perform downstream tasks. However, the parameter space serve
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
arXiv:2604.22778v1 Announce Type: cross Abstract: We present the first systematic study of weight matrix singular value spectra during transformer pretraining, tracking full SVD decompositions of ever
arXiv:2604.22374v1 Announce Type: new Abstract: Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mism
arXiv:2510.05971v3 Announce Type: replace Abstract: The generalization of the Transformer architecture via MetaFormer has reshaped our understanding of its success in computer vision. By replacing sel
arXiv:2601.02438v3 Announce Type: replace-cross Abstract: Software vulnerability detection can be formulated as a binary classification problem that determines whether a given code snippet contains se
arXiv:2604.21741v1 Announce Type: new Abstract: Post-training is essential for turning pretrained generalist robot policies into reliable task-specific controllers, but existing human-in-the-loop pipe
arXiv:2604.21728v1 Announce Type: new Abstract: Pretrained vision-language models such as CLIP exhibit strong zero-shot generalization but remain sensitive to distribution shifts. Test-time adaptation
arXiv:2512.08216v3 Announce Type: replace-cross Abstract: Accurate segmentation of lung tumors from 3D computed tomography (CT) scans is essential for automated treatment planning and response assessm
arXiv:2604.20100v1 Announce Type: new Abstract: Robotic autonomy in open-world environments is fundamentally limited by insufficient data diversity and poor cross-embodiment generalization. Existing r