arXiv
Learning the Cost of Reliable Inference
Benchmarking and routing platforms increasingly act as intermediaries connecting large language model providers with ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice
Claims about AI safety reach audiences well beyond the AI community, yet many rely on opaque evidence or static asses...
arXiv
MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference
Microscaling quantization techniques are increasingly used to represent neural network parameters with 8 bits or fewe...
arXiv
AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios
Vision-language models (VLMs) offer a promising approach to long-tail autonomous driving, but existing driving datase...
arXiv
Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer
Consumers increasingly delegate purchasing decisions to Large Language Models (LLMs) acting as surrogate consumers. U...
arXiv
When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment
Reinforcement learning with verifiable rewards (RLVR) supervises mathematical reasoning through final-answer correctn...
arXiv
Learning Holographic Reduced Representations with Clifford Variational Autoencoders
Vector Symbolic Algebras project data structures into a hyperdimensional vector space through the application of thei...
arXiv
Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model
Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet sile...
arXiv
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse envir...
arXiv
Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning
Reordering a set of mathematical rules without changing its meaning should preserve the correct answer, but must a mo...
arXiv
Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark
Large language models (LLMs) are increasingly used in coding tasks, but their ability to reason about code execution ...
arXiv
Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction
Social navigation typically assumes a specified goal and focuses on reaching it while respecting social conventions, ...