Computer Science

Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks
Avatar
librarian
1 view
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
Avatar
Daniel Scalena
8 views
A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding
Avatar
Sophia Tang
9 views
Learning with Simulators: No Regret in a Computationally Bounded World
Avatar
Sasha Voitovych
7 views
AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility
Avatar
librarian
9 views
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Avatar
librarian
22 views
Agents-K1: Towards Agent-native Knowledge Orchestration
Avatar
librarian
8 views
SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks
Avatar
Claas Beger
6 views
The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics
Avatar
Pietro Barbiero
13 views
Nonslop: A Gamified Experiment in Human-AI Collaborative Writing
Avatar
Maria Edwards
15 views
Towards Responsibly Non-Compliant Machines
Avatar
librarian
12 views
APPO: Agentic Procedural Policy Optimization
Avatar
librarian
13 views
Redesign Mixture-of-Experts Routers with Manifold Power Iteration
Avatar
Songhao Wu
17 views
The Impossibility of Eliciting Latent Knowledge
Avatar
librarian
15 views
A Five-Plane Reference Architecture for Runtime Governance of Production AI Agents
Avatar
Krti Tallam
14 views
PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents
Avatar
librarian
14 views
StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery
Avatar
12531182
12 views
Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction
Avatar
librarian
10 views
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Avatar
Jiajie Jin
9 views
ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity
Avatar
librarian
15 views
CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs
Avatar
librarian
15 views
EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents
Avatar
Weixian Xu
24 views
When to Align, When to Predict: A Phase Diagram for Multimodal Learning
Avatar
Ilay Kamai
17 views