Knowledge catalogue
arXiv:2605.27437v1 Announce Type: cross Abstract: Large Language Models (LLMs) have made significant progress in dialogue, yet redundant memory contexts severely limit their effectiveness in long-term
arXiv:2605.28078v1 Announce Type: cross Abstract: We design a class of additive noise mechanisms that satisfy ((arepsilon, elta))-differential privacy (DP) for scalar, real-valued query functions with
arXiv:2605.28261v1 Announce Type: new Abstract: Instance-level quantification of kidney functional units is essential for morphometric analysis, yet most publicly available pathology datasets provide
arXiv:2605.28769v1 Announce Type: new Abstract: Softmax attention is the cornerstone of modern large language models, but its memory scales linearly and compute quadratically with sequence length. Lin
arXiv:2605.28202v1 Announce Type: new Abstract: Generating collision-free and smooth motions remains a central challenge in robotic manipulation, particularly in cluttered environments and narrow pass
arXiv:2605.28254v1 Announce Type: new Abstract: Robotic locomotion can become efficient when mechanisms exploit passive dynamics, compliance, and resonance rather than track prescribed trajectories. T
arXiv:2605.27408v1 Announce Type: cross Abstract: Partial differential equations (PDEs) are central to modeling physical and engineering systems, but repeatedly solving parametric PDEs remains computa
arXiv:2510.11234v3 Announce Type: replace Abstract: Efficient compression of language model weights is increasingly critical as model scale and deployment grow. Yet, most existing methods rely on hand
📢 New @heyjasper release ! 📢 MONET 🌸 : An Apache2.0 deduped and recaptioned dataset of 105M samples unlocking reproducible text-to-image research. Nano T2I 🖌️ : A codebase to train your own T2I model
arXiv:2604.03799v2 Announce Type: replace Abstract: Autoregressive (AR) models offer stable and efficient training, but standard next-token prediction is not well aligned with the temporal structure r
arXiv:2602.18647v2 Announce Type: replace-cross Abstract: We introduce InfoNoise, an online adaptive noise schedule for diffusion training that reallocates optimization effort toward noise levels wher
arXiv:2605.27616v1 Announce Type: cross Abstract: Real-time anomaly segmentation demands both high recall and efficient low-precision inference. We study the three-way interaction of model architectur
arXiv:2605.27722v1 Announce Type: new Abstract: Two-phase boiling enables heat transfer rates an order of magnitude higher than single-phase cooling, but it remains difficult to model due to the stron
arXiv:2511.20439v2 Announce Type: replace-cross Abstract: In Vision Language Models (VLMs), vision tokens are quantity-heavy yet information-dispersed compared with language tokens, thus consume too m
arXiv:2605.27429v1 Announce Type: cross Abstract: Industrial video-on-demand (VOD) recommenders need richer content understanding, but LLM-as-reranker designs repeat prompt construction, token generat
arXiv:2605.24481v2 Announce Type: replace Abstract: The 1st Cross-Domain EgoCross Challenge at EgoVis, CVPR 2026 evaluates whether multimodal large language models can reason over egocentric videos ac
arXiv:2601.06329v2 Announce Type: replace-cross Abstract: Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving a
arXiv:2605.28057v1 Announce Type: cross Abstract: Test-time adaptation (TTA) aims to adapt models to maintain reliable performance on non-stationary test streams without requiring labeled data. Despit
arXiv:2605.27551v1 Announce Type: new Abstract: The origin of species has been the mystery of mysteries in natural science. By analogy, the origin of synthetic information, we suggest, is the mystery
arXiv:2512.06797v2 Announce Type: replace-cross Abstract: Several problems in machine learning are naturally expressed as the design and analysis of time-evolving probability distributions. This inclu
Our team at @AIatMeta is excited to announce ATLAS: one of the largest automated formalization efforts to date. ATLAS contains Lean 4 formalizations of both statements and proofs from 25+ mathematics
arXiv:2506.10138v3 Announce Type: replace-cross Abstract: We partially reverse-engineer a convolutional recurrent neural network (RNN) trained with model-free reinforcement learning to play the box-pu
arXiv:2505.17720v3 Announce Type: replace Abstract: Artificial intelligence is rapidly reshaping the natural sciences, with weather forecasting emerging as a flagship AI4Science application where mach
arXiv:2605.28226v1 Announce Type: new Abstract: Small-molecule drug discovery requires simultaneous optimization of numerous properties of candidate molecules. These properties can be investigated thr
arXiv:2305.06426v2 Announce Type: replace Abstract: Diabetes is a global health priority, especially in low- and-middle-income countries, where over 50% of premature deaths are attributed to high bloo
arXiv:2605.27832v1 Announce Type: new Abstract: Large Language Models (LLMs) are being applied to increasingly difficult problems and use cases. To navigate their vast solution spaces effectively, LLM
arXiv:2605.28592v1 Announce Type: new Abstract: This note provides an interesting observation on casting partial least square (PLS) as a linearized self-attention so that PLS may be studied within the
arXiv:2605.27631v1 Announce Type: cross Abstract: Code Large Language Models (CLLMs) serve as the core of modern code agents, enabling developers to automate complex software development tasks. In thi
arXiv:2605.28746v1 Announce Type: cross Abstract: This paper studies preference-shaped expected improvement criteria for Bayesian multiobjective optimization. We consider two indicator families which
arXiv:2605.27712v1 Announce Type: new Abstract: Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, P(y=1 mid o_{1
arXiv:2504.12747v2 Announce Type: replace Abstract: The rapid advancement of diffusion models and personalization techniques has made it possible to recreate individual portraits from just a few publi
arXiv:2605.27594v1 Announce Type: cross Abstract: We study the problem of computationally efficient proper agnostic learning of multidimensional concept classes under the Gaussian distribution. In thi
arXiv:2605.28230v1 Announce Type: new Abstract: Modern video generative models produce visually impressive results, yet frequently violate basic physical principles. We propose Proprio, a training-fre
arXiv:2605.27417v1 Announce Type: cross Abstract: With the advent of sixth-generation (6G) mobile communication technology, vehicle-to-everything (V2X) communication faces unprecedented challenges in
arXiv:2605.27942v1 Announce Type: cross Abstract: Principal component analysis (PCA) is traditionally implemented through a covariance or kernel matrix, leading-eigenvector extraction, and hard rank-k
arXiv:2509.14075v2 Announce Type: replace Abstract: Robotic-assisted minimally invasive surgery (RAMIS) requires accurate enforcement of the remote center of motion (RCM) constraint to ensure safe too
arXiv:2601.01616v2 Announce Type: replace Abstract: The textile industry in Bangladesh is one of the most energy-intensive sectors, yet its monitoring practices remain largely outdated, resulting in i
arXiv:2506.05012v2 Announce Type: replace Abstract: Matching the swimming efficiency and agility of fish has remained an elusive goal in underwater robotics. Such locomotion capabilities rely on compl
arXiv:2603.05425v2 Announce Type: replace-cross Abstract: Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine o
arXiv:2605.27813v1 Announce Type: cross Abstract: Text-to-image diffusion models generate images through an iterative denoising process, so internal neural layers produce trajectories of activations r
arXiv:2508.21495v3 Announce Type: replace Abstract: Early-exit neural networks (EENNs) accelerate inference by allowing intermediate classifiers to stop computation once predictions are confident enou
arXiv:2605.27993v1 Announce Type: new Abstract: Object hallucination remains a primary obstacle to the reliable deployment of Multimodal Large Language Models (MLLMs). Current inference-time mitigatio
arXiv:2605.28459v1 Announce Type: new Abstract: Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions, yet existing methods typically
arXiv:2605.27709v1 Announce Type: new Abstract: Mathematical reasoning benchmarks are vital for evaluating large language models (LLMs), but many are static and repeatedly exposed through public evalu
arXiv:2605.27782v1 Announce Type: new Abstract: We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentia
arXiv:2605.28123v1 Announce Type: new Abstract: Prompt-based verification is widely used to mitigate hallucinations in large vision-language models (LVLMs), yet when it helps remains poorly understood
arXiv:2605.28365v1 Announce Type: new Abstract: Lean is increasingly used to judge natural-language mathematical answers, but its signal is partial: many answers never formalize, and a failed proof ma
arXiv:2509.21128v2 Announce Type: replace Abstract: Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on
arXiv:2605.27569v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training records from a deployed model without retraining from scratch. Current protocols ve
arXiv:2605.25767v2 Announce Type: replace Abstract: Synthesizing high fidelity contrast enhanced MRI is clinically valuable for safer and more efficient breast cancer screening, yet remains challengin
arXiv:2605.27947v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot manipulation by using video-based future representations to condition action generation. In pixel-space WAMs, h
arXiv:2605.28602v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for tasks that implicitly reduce to Boolean satisfiability (SAT), yet their reasoning ability on SAT
arXiv:2605.28358v1 Announce Type: cross Abstract: Error-correcting codes enable reliable communication, yet practical soft decoding remains challenging across code families and block lengths. We propo
arXiv:2605.28142v1 Announce Type: cross Abstract: Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so
arXiv:2605.28741v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) are rapidly evolving toward true multimodal reasoning, with visual search representing a concrete instantiation of
arXiv:2510.02329v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates LLM inference by verifying candidate tokens from a draft model against a larger target model. Recent judge de
arXiv:2605.27971v1 Announce Type: cross Abstract: When large language models are fine-tuned to generate persona- or tone-conditioned responses, their output diversity is severely limited--a failure we
arXiv:2602.04898v3 Announce Type: replace-cross Abstract: Text-to-image (T2I) diffusion models are widely adopted for their strong generative capabilities, yet remain vulnerable to backdoor attacks. E
arXiv:2605.28567v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale a
arXiv:2605.28533v1 Announce Type: new Abstract: We introduce a testing-by-betting framework that leverages predictions on unlabeled data to enhance the power of sequential hypothesis testing. Given li