ArXiv Live Feed

Akademik Araştırma
& Analytics.

ArXiv veritabanından canlı olarak çekilen, yapay zeka ve makine öğrenimi alanındaki en son akademik yayınları keşfedin.

PAPER / 3/2/2026

Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions

Selective conformal prediction can yield substantially tighter uncertainty sets when we can identify calibration examples that are exchangeable with the test example. In interventional settings, such as perturbation experiments in genomics, exchangea...

Amir Asiaee, Kavey Aryan, James P. Long
Makaleyi Oku
PAPER / 3/2/2026

Tool Verification for Test-Time Reinforcement Learning

Test-time reinforcement learning (TTRL) has emerged as a promising paradigm for self-evolving large reasoning models (LRMs), enabling online adaptation on unlabeled test inputs via self-induced rewards through majority voting. However, a spurious yet...

Ruotong Liao, Nikolai Röhrich, Xiaohan Wang, Yuhui Zhang, Yasaman Samadzadeh, Volker Tresp, Serena Yeung-Levy
Makaleyi Oku
PAPER / 3/2/2026

Frontier Models Can Take Actions at Low Probabilities

Pre-deployment evaluations inspect only a limited sample of model actions. A malicious model seeking to evade oversight could exploit this by randomizing when to "defect": misbehaving so rarely that no malicious actions are observed during evaluation...

Alex Serrano, Wen Xing, David Lindner, Erik Jenner
Makaleyi Oku
PAPER / 3/2/2026

Adaptive Confidence Regularization for Multimodal Failure Detection

The deployment of multimodal models in high-stakes domains, such as self-driving vehicles and medical diagnostics, demands not only strong predictive performance but also reliable mechanisms for detecting failures. In this work, we address the largel...

Moru Liu, Hao Dong, Olga Fink, Mario Trapp
Makaleyi Oku
PAPER / 3/2/2026

Conformal Policy Control

An agent must try new behaviors to explore and improve. In high-stakes environments, an agent that violates safety constraints may cause harm and must be taken offline, curtailing any future interaction. Imitating old behavior is safe, but excessive ...

Drew Prinster, Clara Fannjiang, Ji Won Park, Kyunghyun Cho, Anqi Liu, Suchi Saria, Samuel Stanton
Makaleyi Oku
PAPER / 3/2/2026

From Leaderboard to Deployment: Code Quality Challenges in AV Perception Repositories

Autonomous vehicle (AV) perception models are typically evaluated solely on benchmark performance metrics, with limited attention to code quality, production readiness and long-term maintainability. This creates a significant gap between research exc...

Mateus Karvat, Bram Adams, Sidney Givigi
Makaleyi Oku
PAPER / 3/2/2026

Symbol-Equivariant Recurrent Reasoning Models

Reasoning problems such as Sudoku and ARC-AGI remain challenging for neural networks. The structured problem solving architecture family of Recurrent Reasoning Models (RRMs), including Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM)...

Richard Freinschlag, Timo Bertram, Erich Kobler, Andreas Mayr, Günter Klambauer
Makaleyi Oku
PAPER / 3/2/2026

Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillation

We present Sketch2Colab, which turns storyboard-style 2D sketches into coherent, object-aware 3D multi-human motion with fine-grained control over agents, joints, timing, and contacts. Conventional diffusion-based motion generators have advanced real...

Divyanshu Daiya, Aniket Bera
Makaleyi Oku
PAPER / 3/2/2026

Multi-Head Low-Rank Attention

Long-context inference in large language models is bottlenecked by Key--Value (KV) cache loading during the decoding stage, where the sequential nature of generation requires repeatedly transferring the KV cache from off-chip High-Bandwidth Memory (H...

Songtao Liu, Hongwu Peng, Zhiwei Zhang, Zhengyu Chen, Yue Guo
Makaleyi Oku

ArXiv API Entegrasyonu

Bu sayfa doğrudan arXiv.org veritabanından veri çekmektedir. Listelenen tüm içerikler global akademik topluluk tarafından paylaşılan open-access yayınlardır.

arXiv.org'u Keşfet