GitHub 新星
10 条
arXiv 论文
10 条
-
1
Rethinking the design space of Vanilla Pixel Diffusion Transformers
Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the lossy latent bottleneck and separately trained autoencoder. JiT shows that a vanillaSoumik Mukhopadhyay, Long Mai, Abhinav Shrivastava
-
2
Behavioral Couplings: From Formation to Behavioral Emergence in Language Models
Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more sycophantic, and training it to wrDongyoon Hahm, Woogyeol Jin, Dennis Wei
-
3
AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery
Reproducible and analytically robust research findings are essential to scientific progress, but evaluating these properties typically requires costly manual effort. We investigate whether LLM agentsShicheng Liu, Krista Opsahl-Ong, Andrew Drozdov
-
4
Task-aligned spectral inductive biases in parameterized quantum circuits
Parameterized quantum circuits are widely investigated in quantum machine learning, yet how their architecture can provide task-aligned inductive biases remains poorly understood. We study data reuploFelix Frohnert, Adrián Pérez-Salinas, Sebastian Lange
-
5
Beyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation
A reasoning trace can accompany a correct answer without providing effective supervision for a particular student. We study how to construct traces that improve learning beyond answer-only supervisionShaoang Li, Yanhang Shi, Yufei Li
-
6
Waiting Buys Exactly Two Moments: Endogenous Identification in Prediction-Driven Allocation
A planner with a fixed budget of preventive help must decide whom to help and when. Waiting reveals risk but removes intervention opportunities as higher-risk individuals leave first. We characterizeRama AlHamidi, Rasul Khanbayov, Erchin Serpedin
-
7
Quality-of-Transmission Estimation in Quantum Networks: Compute, Simulate, or Learn?
Future quantum networks will rely on control-plane decisions such as routing, scheduling, entanglement provisioning, purification, and memory allocation. Each decision depends on a timely and reliableAnis Bekri, Amar Abane, Van Sy Mai
-
8
Self-Building Labs
Self-driving laboratories (SDLs) accelerate scientific discovery by automating experimental execution and optimization. AI agents can increasingly propose new experiments, but existing SDLs can only rJiaru Bai, Yuchi Zhao, Han Hao
-
9
ENFR: Evidence Networks with Flow-Matched References for Amortized Simulation-Based Model Inference
The evidence, $\mathcal{Z} = p(x | \mathcal{M})$, of a data-generating model $\mathcal{M}$ is a powerful tool in Bayesian frameworks: it enables model inference, model misspecification tests, and goodKai Lehman, Jameson Dong, Carolina Cuesta-Lazaro
-
10
Learning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphere
Many of the most important datasets in the physical sciences live natively on the sphere, and these data often carry no preferred position or orientation. Using methods that do not reflect this symmetJoshua Williamson, Niall Jeffrey, Lorne Whiteway
Hacker News
10 条
- 1 Timestral: Mistral's time-series foundation models
- 2 Wine ported to OpenBSD
- 3 It's still ok to enjoy programming
- 4 MiniMax M3.1 Flash
- 5 I built a drone with only one motor [video]
- 6 Alternatives to animal testing are finally taking off
- 7 Starcraft: Ashfall
- 8 Android apps running native on macOS
- 9 Ask HN: How to deal with shipping AI-written code you don't understand?
- 10 Let's Encrypt is adding two additional remote perspectives for domain validation