技术雷达 · 2026-09-04

G GitHub 新星 10 条

A arXiv 论文 10 条

1 A Common Measure of Communication for Speech Brain-Computer Interfaces cs.LGq-bio.NC
Speech brain-computer interfaces (speech BCIs) translate neural activity into language, offering a path towards restoring speech for people with paralysis and, more broadly, enabling new forms of natu
Dulhan Jayalath, Benjamin Ballyk, Oiwi Parker Jones
2 Discriminative World Models for Web Agents cs.AIcs.LG
Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them with a ranker model or a Process Reward Model (PR
Kelvin Li, Dhruv Pendharkar, Anish Pahilajani
3 Graph Machine: Towards Better Pretraining via Edges cs.LG
We introduce the Graph Machine (GM), an architecture that maintains an $O(n)$-sized state and accesses it through sparse, dynamic routing. Unlike methods with fixed-size states or sparse but static ro
Lintai Hou
4 GRADSOLVE: fast exact gradients for ODE ensembles on GPUs cs.MScs.DCcs.LG
Ordinary differential equations (ODEs) underlie models in science and engineering, and many applications need derivatives of their solutions with respect to parameters. Ensembles of independent trajec
Alessio Spurio Mancini
5 Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework cs.ROcs.AI
Autonomous robots powered by deep learning face a fundamental auditability challenge: when incidents occur, investigators cannot reconstruct why the system made specific decisions. This paper presents
Cagri Temel
6 Improved Gradient Descent Lower Bounds Beyond Nesterov math.OCcs.LGstat.ML
We study how far gradient descent (GD) can be accelerated by predetermined stepsizes in smooth convex optimization. Going beyond the classical $Ω(n^{-2})$ first-order oracle lower bound of Nemirovsky
Yuhan Ye, Kaizhao Liu
7 The Implications of Linguistic Illegibility for LLM Security cs.LGcs.CR
LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic features can be an u
James Mickens
8 Post-Training Language Models for Gold-Medal Performance in Coding Competitions cs.LGcs.AIcs.CL
Competitive programming has become a key test of large language model reasoning, with international competitions such as IOI and ICPC representing its most challenging settings. We present an end-to-e
Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi
9 UE5M3 FP4 Block Scaling for Stable Language Model Pretraining cs.LG
Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer Engine \nv{} recipe addresses this with current-t
Robert Hu, Carlo Luschi, Paul Balanca
10 Learning Spectral-Like Mesh-Free Discretisations physics.comp-phcs.LG
Meshfree methods such as smoothed particle hydrodynamics (SPH) with kernel corrections, radial basis function-generated finite differences (RBF-FD), and the local anisotropic basis function method (LA
Lucas Gerken Starepravo, Henry Broadley, Steven Lind

H Hacker News 10 条