Paper Archive

Browse and export your curated research paper collection

403
Archived Days
3953
Total Papers
7.3
Avg Score
12
Categories

Export Archive Data

Download your archived papers in various formats

JSON: Complete data with analysis | CSV: Tabular data for analysis | Markdown: Human-readable reports | BibTeX: Academic citations
Browse by Date

Papers for November 4, 2026

10 papers found

[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 learning

Unified 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...

Keywords: multimodal dialogue, stateful interaction, dataset, benchmark, unified multimodal models, image editing, visual reasoning, multi-turn dialogue

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/3/2026 huggingface

datasets

We 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 ...

Keywords: surgical vision, multi-endoscope dataset, RAMIS, novel view synthesis, geometric generalization, foundation models, benchmark

[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 processing

Later 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...

Keywords: long-context, context-compaction, semantic-state-space-models, LLM-efficiency, frontier-models, software-engineering-agents

[object Object], [object Object], [object Object], [object Object], [object Object] 11/3/2026 huggingface

generative models

Probabilistic 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...

Keywords: Koopman operators, probabilistic forecasting, flow matching, time-series, uncertainty quantification, generative models

[object Object] 11/3/2026 huggingface

transformer architectures

Byte 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...

Keywords: byte-level language models, multiscale architecture, invertible subband transform, fast weight memory, DeepMem

Jisoo Kim, Chaehyun Kim, Junsu Kim, Jiho Park, Seongchan Kim, Eunbeen Hong, Soowon Son, Fu-En Yang, Seungryong Kim 11/3/2026 arxiv

robotics

Learning 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...

Keywords: video diffusion models, latent action learning, cross-embodiment transfer, robotics, generative models, action representation

Qi Yang, Yingzhan Xu, Kai Zhang, Li Zhang 11/3/2026 arxiv

computer vision

This 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 ...

Keywords: 3D Gaussian Splatting, video compression, spherical harmonics, rate-distortion optimization, standard video codecs

Teerawat Tongloy, Jiraporn Pongsopa, Rangsan Jomtarak 11/3/2026 arxiv

natural language processing

When 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...

Keywords: Born measurement, quantum-inspired attention, exact interpretability, integrated gradients, e-SNLI, quantum circuits, optoelectronic computing, transformer architectures

Sílvia Casacuberta, Parikshit Gopalan, Varun Kanade, Omer Reingold, Konstantinos Stavropoulos, Pranay Tankala 11/3/2026 arxiv

machine learning

Given 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...

Keywords: agnostic learning, multiaccuracy, computational learning theory, oracle reductions, no-regret learning, boosting, generative modeling

Hongyin Luo, Wei Fang, Lijie Yang, Owen Stepan, Daniel Suit, Jeff Krapf, Dana Wensberg, Jack O'Brien 11/3/2026 arxiv

natural language processing

Speculative 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 ...

Keywords: speculative decoding, long-horizon agents, adversarial training, reasoning accuracy, draft model, verification noise
Loading...

Preparing your export...