Browse and export your curated research paper collection
[object Object], [object Object], [object Object] 11/12/2026 huggingface
machine learningMemory 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...
[object Object], [object Object], [object Object] 11/12/2026 huggingface
ethics aiWe 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...
[object Object], [object Object] 11/12/2026 huggingface
computer visionReference-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...
[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 learningDecision 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...
[object Object], [object Object], [object Object], [object Object], [object Object] 11/12/2026 huggingface
machine learningNeural 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 ...
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 visionDecoder-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 ...
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 modelsFrontier 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...
Felix O'Mahony, Daniel Olmeda Reino, Roberto Cipolla, Ayush Tewari 11/12/2026 arxiv
generative modelsVideo 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...
Ethan Lin, Akanksha Sarkar, Ziang Liu, Kristin Branson, Jennifer J. Sun 11/12/2026 arxiv
machine learningApplying 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 ...
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 learningHow 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...
Preparing your export...