Papers
297 items in the last 7 days · RSS:/feed/category/paper.xml
Trending in this category
1
When Cooperation Must Change: Semantic Strategy Unlearning in Multi-Agent Reinforcement Learning
2
ERGo: Energy-Efficient Hybrid Graph Neural Network Training on Processing-In-Memory Architectures
3
LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular Learning
4
Identifying Latent Neural Dynamics with Recognition-Parametrised Gaussian Process Dynamical Systems
5
Robots that Collaborate: Sequential Asymmetric Imitation for Learning Coupled Robot Policies
6
Disturbance-Aware Informative Planning in Spatiotemporal Environments
Latest
Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent
arXiv:2611.18397v1 Announce Type: new Abstract: We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive e
pts
WeatherDreamer: Learning a World Model from Multimodal Earth Observations
arXiv:2611.18393v1 Announce Type: new Abstract: Machine learning weather models now rival operational global forecasts but still start from analyses p
pts
Reasoning Models Confabulate to Defend Injected Beliefs About Their Own Requests
arXiv:2611.17958v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring and self-report are proposed as levers for AI oversight, on the assu
pts
Choosing Quantized Code LLMs by File Size and Energy per Solved Task
arXiv:2611.17605v1 Announce Type: new Abstract: A developer running a code assistant on a laptop downloads one model file, and local inference moves t
pts
Express Language Modeling
arXiv:2606.10944v5 Announce Type: replace-cross Abstract: We introduce a new tool, Express, for converting a non-causal attention approximation into a
pts
Contagious Fingerprints: When LLMs Inherit Another Model's Identity
arXiv:2611.18104v1 Announce Type: new Abstract: The fingerprint by which a classifier recognizes the LLM behind a text is usually treated as a fixed p
pts
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
arXiv:2510.08697v3 Announce Type: replace Abstract: Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from h
pts
X-Nav Technical Report: Real-World Long-Horizon Indoor-to-Outdoor Navigation on a Humanoid Robot
arXiv:2611.17598v1 Announce Type: new Abstract: Long-horizon navigation from indoors to outdoors remains an open problem for humanoid robots: one inst
pts