· ai
[Paper] Structured Document Translation via Format Reinforcement Learning
Recent works on structured text translation remain limited to the sentence level, as they struggle to effectively handle the complex document-level XML or HTML ...
-
- · ai
[Paper] SA-IQA: Redefining Image Quality Assessment for Spatial Aesthetics with Multi-Dimensional Rewards
In recent years, Image Quality Assessment (IQA) for AI-generated images (AIGI) has advanced rapidly; however, existing methods primarily target portraits and ar...
- · ai
[Paper] Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction
Although diffusion models now occupy a central place in generative modeling, introductory treatments commonly assume Euclidean data and seldom clarify their con...
- · ai
[Paper] The Geometry of Intelligence: Deterministic Functional Topology as a Foundation for Real-World Perception
Real-world physical processes do not generate arbitrary variability: their signals concentrate on compact and low-variability subsets of functional space. This ...
- · ai
[Paper] David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?
Large Language Model(LLM) inference demands massive compute and energy, making domain-specific tasks expensive and unsustainable. As foundation models keep scal...
- · ai
[Paper] Multi-LLM Collaboration for Medication Recommendation
As healthcare increasingly turns to AI for scalable and trustworthy clinical decision support, ensuring reliability in model reasoning remains a critical challe...
- · software
[Paper] Configuration Defects in Kubernetes
Kubernetes is a tool that facilitates rapid deployment of software. Unfortunately, configuring Kubernetes is prone to errors. Configuration defects are not unco...
- · ai
[Paper] Meta-Learning for Quantum Optimization via Quantum Sequence Model
The Quantum Approximate Optimization Algorithm (QAOA) is a leading approach for solving combinatorial optimization problems on near-term quantum processors. How...
- · ai
[Paper] Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inferen...
- · ai
[Paper] Plug-and-Play Homeostatic Spark: Zero-Cost Acceleration for SNN Training Across Paradigms
Spiking neural networks offer event driven computation, sparse activation, and hardware efficiency, yet training often converges slowly and lacks stability. We ...
- · ai
[Paper] Factuality and Transparency Are All RAG Needs! Self-Explaining Contrastive Evidence Re-ranking
This extended abstract introduces Self-Explaining Contrastive Evidence Re-Ranking (CER), a novel method that restructures retrieval around factual evidence by f...
- · ai
[Paper] Evolutionary Architecture Search through Grammar-Based Sequence Alignment
Neural architecture search (NAS) in expressive search spaces is a computationally hard problem, but it also holds the potential to automatically discover comple...