· ai
[Paper] Testing the Machine Consciousness Hypothesis
The Machine Consciousness Hypothesis states that consciousness is a substrate-free functional property of computational systems capable of second-order percepti...
-
- · ai
[Paper] Joint Partitioning and Placement of Foundation Models for Real-Time Edge AI
Inference over large-scale foundation models within heterogeneous edge environments necessitates a fundamentally reconfigurable orchestration substrate. Static ...
- · devops
[Paper] Elastic Mixture of Rank-Wise Experts for Knowledge Reuse in Federated Fine-Tuning
Federated fine-tuning offers a promising solution for adapting Large Language Models (LLMs) to downstream tasks while safeguarding data privacy. However, its hi...
- · ai
[Paper] FC-ADL: Efficient Microservice Anomaly Detection and Localisation Through Functional Connectivity
Microservices have transformed software architecture through the creation of modular and independent services. However, they introduce operational complexities ...
- · ai
[Paper] Soft Quality-Diversity Optimization
Quality-Diversity (QD) algorithms constitute a branch of optimization that is concerned with discovering a diverse and high-quality set of solutions to an optim...
- · devops
[Paper] SIMPLE: Disaggregating Sampling from GPU Inference into a Decision Plane for Faster Distributed LLM Serving
As large language models (LLMs) scale out with tensor parallelism (TP) and pipeline parallelism (PP) and production stacks have aggressively optimized the data ...
- · ai
[Paper] Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models
Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning trace...
- · ai
[Paper] Video-CoM: Interactive Video Reasoning via Chain of Manipulations
Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still 'think about videos' ie once a video is encoded, reasoning unf...
- · ai
[Paper] Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction
Developing robust world model reasoning is crucial for large language model (LLM) agents to plan and interact in complex environments. While multi-turn interact...
- · ai
[Paper] AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement
Recently, multi-person video generation has started to gain prominence. While a few preliminary works have explored audio-driven multi-person talking video gene...
- · ai
[Paper] ThetaEvolve: Test-time Learning on Open Problems
Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that ev...
- · ai
[Paper] Visual Generation Tuning
Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned wi...