Akademik Araştırma
& Analytics.
ArXiv veritabanından canlı olarak çekilen, yapay zeka ve makine öğrenimi alanındaki en son akademik yayınları keşfedin.
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...
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...
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...
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...
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 ...
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...
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)...
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...
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...
ArXiv API Entegrasyonu
Bu sayfa doğrudan arXiv.org veritabanından veri çekmektedir. Listelenen tüm içerikler global akademik topluluk tarafından paylaşılan open-access yayınlardır.