GitHub 新星
10 条
arXiv 论文
10 条
-
1
Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion
Recent advances in robot learning have driven rapid progress in humanoid control, enabling increasingly agile behaviors in the real world. However, humanoid control networks are typically obtained thrHuixuan Cheng, Bike Zhang, Shankar Sastry
-
2
Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance
Mobile Manipulation (MoMa) is a cornerstone of autonomous robotic systems, yet real-world fine-tuning remains a formidable challenge because of high-dimensional action spaces and intricate coupling beZhefei Gong, Hefeifei Jiang, Zehao Wang
-
3
Co-Evolving Acting and Forecasting for Language Agents
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervisionHaofei Yu, Yixing Chen, Yining Zhao
-
4
Your Transformer Is Secretly Elastic
Scaling up transformers has produced models with broad capabilities, deployed across heterogeneous hardware and fluctuating workloads. Yet, model families offer only a few fixed sizes (e.g., S, B, L),Walter Simoncini, Dheeraj Varghese, Gertjan J. Burghouts
-
5
Price of Anarchy of First-Price Auctions in Agentic Markets
An agentic market is a decentralized serving-time market where AI agents bid to claim each user prompt. An agent's bid is based on its expected value for the prompt, which is the expectation of the reShubhendu Trivedi, Jacob Eisenstein, Alekh Agarwal
-
6
Continuum Attention
We introduce Continuum Attention (CA), a causal Transformer attention operator that replaces discrete key and value lookup with integration over a continuous, piecewise linear memory curve. Each queryAfshin Khadangi
-
7
Learnable Hodge-Laplacian Driven Mixture of Experts for Steady-PDE Surrogates on Coarse Unstructured Meshes
Current approaches for steady partial differential equations surrogate models on unstructured meshes apply a single mixing mechanism to the whole solution. This paper proposes an architecture that parStavros Nousias, Akis Nousias, Konstantinos Gkrispanis
-
8
Player-1: Learning to Play from Synthetic Experience
Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their visually rich worlds and diverse mechanics, remaiMingyu Ouyang, Yiran Wang, Siyuan Hu
-
9
Latent Compaction with Test-Time Training
Long contexts enlarge key--value (KV) caches, increasing memory use and attention costs during generation. Compressing these caches must preserve information for unseen questions. We introduce **LatenYingfa Chen, Xingyu Shen, Chaojun Xiao
-
10
One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness
Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as renaming an action or changing the notation, leaveArtin Tajdini, Manpreet Kaur, Peng Qi
Hacker News
10 条
- 1 Muse Spark Open
- 2 Neural networks are clean
- 3 Wayland desktop for Linux with skeuomorphic design
- 4 AdFection: Targeted ads turned into a pipeline for zero-click mercenary spyware
- 5 Wanted to download an ISO, ended up writing a kernel exploit
- 6 I know why the mathematicians weep
- 7 Jev meets the Trolley Problem
- 8 Steam Client is now faster than Epic's new vibe coded launcher
- 9 Show HN: Unfenced – Land for sale that borders public land
- 10 Libreboot 26.10 "Ominous Olive" released with UEFI, Chromebook support