Browse and export your curated research paper collection
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/3/2026 huggingface
multimodal learningUnified Multimodal Models (UMMs) integrate visual understanding, generation, and editing within a single unified framework. However, existing unified multimodal datasets and benchmarks remain dominated by single-turn tasks. Even in recent multi-turn datasets, many turns can be solved independently w...
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/3/2026 huggingface
datasetsWe introduce iMED, the first synchronized multi-endoscope dataset for robot-assisted minimally invasive surgery (RAMIS), designed to address a fundamental limitation in surgical vision benchmarking: the absence of independent held-out viewpoints. Existing surgical datasets capture single-trajectory ...
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/3/2026 huggingface
natural language processingLater tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x. Through frequent compaction, we show across a broad range of long-horizon and long-input tasks that frontier language models sacrifice little to no task accurac...
[object Object], [object Object], [object Object], [object Object], [object Object] 11/3/2026 huggingface
generative modelsProbabilistic time-series forecasting requires models that simultaneously capture structured temporal dynamics, expressive uncertainty, and efficient inference, yet existing approaches fall short of this goal: latent dynamical models impose structure but rely on restrictive generation mechanisms, wh...
[object Object] 11/3/2026 huggingface
transformer architecturesByte level language models avoid tokenizer dependence and provide universal coverage, but processing every byte at full resolution is expensive. We introduce DeepMem, a causal multiscale architecture that separates semantic compression from exact byte preservation. A learned invertible subband trans...
Jisoo Kim, Chaehyun Kim, Junsu Kim, Jiho Park, Seongchan Kim, Eunbeen Hong, Soowon Son, Fu-En Yang, Seungryong Kim 11/3/2026 arxiv
roboticsLearning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embodiment and appearance. Existing latent action models infer actions from visual transitions, but their representations of...
Qi Yang, Yingzhan Xu, Kai Zhang, Li Zhang 11/3/2026 arxiv
computer visionThis paper presents GSCV++, a lightweight pipeline for 3D {G}aussian {S}platting (GS) sequences {C}ompression with standard {V}ideo codecs. To meet the requirements of low-complexity and hardware compatibility from the industry, GSCV++ jointly improves preprocessing, 3D-to-2D mapping, and practical ...
Teerawat Tongloy, Jiraporn Pongsopa, Rangsan Jomtarak 11/3/2026 arxiv
natural language processingWhen a language model answers, we can usually only estimate why. We build a transformer in which every step is a Born measurement - attention $|\langle q|k\rangle|^4$ normalised over each row, a measured product in place of the feed-forward nonlinearity, and a Born readout. With its denominators hel...
Sílvia Casacuberta, Parikshit Gopalan, Varun Kanade, Omer Reingold, Konstantinos Stavropoulos, Pranay Tankala 11/3/2026 arxiv
machine learningGiven a class of machine learning models and sample access to a data distribution with binary labels, which computational task is harder: training a discriminative model that distinguishes positive and negative labels as well as the best member of the class, or training a generative model whose outp...
Hongyin Luo, Wei Fang, Lijie Yang, Owen Stepan, Daniel Suit, Jeff Krapf, Dana Wensberg, Jack O'Brien 11/3/2026 arxiv
natural language processingSpeculative decoding has been treated purely as a systems optimization that speeds up large language model decoding without changing the model behavior. Under this view, the growing effort to train better draft models has been focused solely on acceptance rate. We argue that this view does not hold ...
Preparing your export...