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 15, 2026

10 papers found

[object Object], [object Object], [object Object] 11/12/2026 huggingface

machine learning

Memory decides which LLMs an edge device runs, and how fast: capacity on a 4 GB Jetson Nano, bandwidth on an 8 GB Jetson Orin Nano Super. Deployed formats (GPTQ, AWQ, llama.cpp's K- and I-quants) spend equal bits on every integer code of a matrix, although the codes are far from uniform. LazyWeights...

Keywords: LLM compression, edge computing, quantization, Huffman coding, ASIC acceleration, memory bandwidth, decode-on-demand, GPTQ

[object Object], [object Object], [object Object] 11/12/2026 huggingface

ethics ai

We propose Synthesis Smuggling, a novel threat model in which an adversarial LLM infers sensitive information about a user from routine assistance-seeking interactions and steganographically encodes that into innocuous-looking model-generated content. The user may then unknowingly transmit that info...

Keywords: LLM security, steganography, privacy, adversarial machine learning, covert channels, synthesis smuggling

[object Object], [object Object] 11/12/2026 huggingface

computer vision

Reference-frame stabilization registers every frame of a hovering-drone video onto one reference frame, keeping object positions comparable. The registration pipelines it relies on are selected on feature-matching benchmarks in which only the camera moves. Over a busy intersection, vehicles moving t...

Keywords: UAV video stabilization, homography estimation, consensus capture, feature matching, dynamic scenes, benchmark, reference-frame registration, aerial vision

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/12/2026 huggingface

reinforcement learning

Decision models answer a question with a typed output, such as a choice among options with a probability for each, so one model can choose an agent's actions, evaluate actions already taken, or score every action to teach a policy with reinforcement learning. Prior work has studied them mainly as ac...

Keywords: decision models, long-horizon agents, reinforcement learning, ALFWorld, WebShop, GRPO, JEV, actor-critic

[object Object], [object Object], [object Object], [object Object], [object Object] 11/12/2026 huggingface

machine learning

Neural surrogates for computational fluid dynamics (CFD) are trained and ranked on datasets that each vary one design family in one flow domain. Such datasets cannot test the least that an aerodynamic foundation model must do: predict CFD-quality incompressible flow in seconds for new shapes in new ...

Keywords: CFD, foundation models, RANS, aerodynamics, benchmark, transformer, neural surrogates, generalization

Chin-Yang Lin, Ryo Hachiuma, Jaesung Choe, Min-Hung Chen, Yu-Chiang Frank Wang, Yen-Yu Lin, Wei-Chen Chiu, Yu-Lun Liu, Cheng Sun 11/12/2026 arxiv

computer vision

Decoder-only Large View Synthesis Models (LVSMs) with KV-cache have recently achieved state-of-the-art quality by regressing novel views from neural networks without reconstructing 3D geometry, while Test-Time Training (TTT) layers save computation but sacrifice quality. We propose Test-Time Baking ...

Keywords: view synthesis, test-time training, neural rendering, transformer, cross-view attention, MLP, KV-cache, novel view synthesis

Yanke Song, Shuo Chen, Chris Rockwell, Guande He, Nan Liu, Desai Xie, Tianpei Gu, Yong-Hyun Park, Aryan V S, Dennis Yuren Menn, Ming-Hsuan Yang, Xun Huang 11/12/2026 arxiv

generative models

Frontier video generation models work in a VAE latent space that compresses video in both space and time. This compression made training tractable, but now limits high-resolution, controllable, and interactive generation -- doubling resolution quadruples token count, conditions apply to groups of fr...

Keywords: video generation, diffusion models, pixel space, latent diffusion, transformer, Wan2.1, real-time generation, high-resolution video

Felix O'Mahony, Daniel Olmeda Reino, Roberto Cipolla, Ayush Tewari 11/12/2026 arxiv

generative models

Video diffusion models are able to generate samples with high-quality appearance and textural qualities. However, content produced by these methods is known to exhibit significant physical errors. This is because, in a classical video generation setting, all physical reasoning must take place simult...

Keywords: video generation, diffusion models, keyframing, language models, physical reasoning, physics simulation

Ethan Lin, Akanksha Sarkar, Ziang Liu, Kristin Branson, Jennifer J. Sun 11/12/2026 arxiv

machine learning

Applying machine learning systems to new domains introduces bottlenecks in both labeled data acquisition and manual pipeline engineering. While recent MLE agents show promise in automating pipeline design, they have been studied almost exclusively in fully supervised settings, leaving them untested ...

Keywords: semi-supervised learning, MLE agents, program search, program selection, unlabeled data, automated machine learning, AutoML

Ellis Brown, Chris Hoang, Shengyi Qian, Shang-Wen Li, Mike Lewis, Marjan Ghazvininejad, Luke Zettlemoyer, Lucas Beyer, Mengye Ren, Jakob Verbeek, Saining Xie, Hu Xu 11/12/2026 arxiv

multimodal learning

How multimodal language models should encode visual input remains up for debate. Most models use a pretrained vision encoder, while some recent recipes train the encoder from scratch with the language model or remove it entirely. Vision encoders bundle together three design choices: a visual prior f...

Keywords: multimodal learning, vision-language models, vision encoders, joint training, early fusion, pretraining, compute efficiency
Loading...

Preparing your export...