GitHub 新星
10 条
arXiv 论文
10 条
-
1
Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We intPrakhar Kaushik, Soumava Paul, Alan Yuille
-
2
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot demonstraChaehyun Kim, Chi-Pin Huang, Jisoo Kim
-
3
When Should We Intervene at Test Time?
Test-time adaptation helps a deployed model respond to changing inputs, but the same intervention can rescue one batch and damage the next. Updating normalization statistics, for example, can improveJiahao Zhang, Xinling Wen, Liangliang Li
-
4
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should redistriIgor Shilov, Xiaoxue Yang, Alexander Panfilov
-
5
Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops
Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father's mother is not a mother's faAakash Sarkar, Ananya Mukherjee, Motoshige Sato
-
6
KPPax: preprocess differentiable kinetic ODE for machine learning in atmospheric chemistry
Atmospheric chemical mechanisms are commonly distributed in the language of the Kinetic PreProcessor (KPP), which generates efficient Fortran or C code but does not fit into the differentiable programWenqing Peng, Michael Boy, Zhi-Song Liu
-
7
Pushing Dexterity and Safety for In-Hand Object Pose Reaching That Works Remarkably Well
Dexterous manipulation with multi-fingered hands is the next frontier of robotics, yet learned hand skills remain limited to simple grasps or basic repeated motions, such as rotating an object. As robIan Chuang, Hiya Shah, Vamsi Chilamkur
-
8
Can LLMs Uncover Hidden Physical Laws through Free Exploration?
Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavioZhen Yang, Wen Wang, Xander Xu
-
9
Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis
We explore how to build performant large language model (LLM) tool-use agents that complete complex, multi-step tasks. Specifically, we study how data composition in synthetically generated tool-use eAndrew Szot, Samira Abnar, Omar Attia
-
10
MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control
Weight decay and explicit weight-norm constraints improve optimizer performance in language model pretraining, yet a unified understanding of why such control helps and how much is needed remains incoAthanasios Glentis, Dawei Li, Mingyi Hong
Hacker News
10 条
- 1 Apple's git still trusts the compromised eMudhra certificates
- 2 Why is this fingerprinting script creating bioweapons?
- 3 Gemini 4 Carbon
- 4 Start Doing Graph Theory
- 5 MacBook Pro with PROLED XDR Display and Touch
- 6 The Grid, a factory-scale robot in Massachusetts that builds PCBs on demand
- 7 Emacs Turns 50
- 8 CNC Stone Carving
- 9 Dayjob: Tax – evaluating AI agents on 50 professional tax assignments
- 10 AlpineBSD