arXiv Machine Learning
Aug 11
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
arXiv:2608. 09444v1 Announce Type: new Abstract: A main promise of looped language models (LMs) is depth-adaptive inference.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv AI
Aug 11
Adaptive Two-Level Allocation of a Conserved Capacity Budget Across Locations and Service Classes
arXiv:2608. 07747v1 Announce Type: new Abstract: We study how to share a single conserved capacity budget across many locations and two service classes when demand is uneven, time-varying, and can exceed supply.
arXiv AI
Aug 11
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
arXiv:2608. 08638v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools.
arXiv AI
Aug 11
Mismatch Matters: On-Policy Distillation Beyond Token Agreement
arXiv:2608. 09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repetitive loops to achieve near-perfect token agreement with the teacher despite globally flawed responses.
arXiv Machine Learning
Aug 11
From Independent to Correlated Diffusion: Generalized Generative Modeling with Probabilistic Computers
arXiv:2603. 27996v2 Announce Type: replace Abstract: Diffusion models have emerged as a powerful framework for generative tasks in deep learning.
arXiv Machine Learning
Aug 11
MoE-Prism: Disentangling Monolithic Experts for Elastic MoE Services via Model-System Co-Designs
arXiv:2510. 19366v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) scales model capacity through sparse activation, and is becoming an important architecture for large language models (LLMs).
arXiv Machine Learning
Aug 11
Flow-based conditional cardiac anatomy generation for virtual cohorts
arXiv:2608. 09460v1 Announce Type: new Abstract: Cardiac digital twin research is moving from subject-specific anatomical replicas toward virtual cohorts that represent clinically relevant population subgroups.
arXiv AI
Aug 11
LITEWAY: LIghtweight HAR via Temporal Efficient highWAY
arXiv:2608. 09421v1 Announce Type: cross Abstract: Wearable human activity recognition (HAR) remains challenging due to the computational and energy constraints of deep learning models on resource-limited devices.
arXiv AI
Aug 11
RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning
arXiv:2604. 16694v2 Announce Type: replace Abstract: Large reasoning models (LRMs) enhance problem-solving capabilities by generating explicit multi-step chains of thought (CoT) reasoning; however, they incur substantial inference latency and computational overhead.
arXiv Machine Learning
Aug 11
CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents
arXiv:2608. 07855v1 Announce Type: new Abstract: Multi-turn Reasoning-and-Acting (ReAct) agents accumulate growing trajectories of reasoning, tool calls, and observations.
arXiv AI
Aug 11
Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification
arXiv:2608. 08195v1 Announce Type: cross Abstract: Large language models (LLMs) are high-value assets that can be derived through redeployment, fine-tuning, quantization, or further alignment.
arXiv AI
Aug 11
Eco-SoC: A Sustainable VLSI Architecture for Energy-Proportional Artificial Intelligence
arXiv:2608. 08761v1 Announce Type: cross Abstract: In an era defined by escalating climate change and the pervasive deployment of edge intelligence, the environmental cost of semiconductor manufacturing and operation has reached a critical threshold.
arXiv AI
Aug 11
How Simple Can It Get? From Interpretable Equations to Readable Rules for Financial Decision Making
arXiv:2608. 09433v1 Announce Type: cross Abstract: In regulated domains such as finance, a model that cannot be explained cannot be deployed, yet many interpretable classifiers defeat their own purpose by producing formulas with dozens of features that no regulator could read.
arXiv AI
Aug 11
DistillCache: KL-Guided Adaptive KV-Cache Eviction for Memory-Efficient LLM Inference
arXiv:2608. 08878v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) achieve strong performance across many tasks, but their Key-Value (KV) cache grows linearly with sequence length, creating a severe memory bottleneck for long-context inference.
arXiv AI
Aug 11
LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs
arXiv:2608. 07733v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) are widely used across domains such as natural sciences, social network analysis, chip design, and recommendation systems.
arXiv Machine Learning
Aug 11
EFFEKT: Efficient Federated Knowledge Transfer to Foundation Models
arXiv:2608. 08138v1 Announce Type: cross Abstract: Recent data protection laws have accelerated the adoption of Federated Learning (FL) for privacy-preserving decentralized training.
arXiv AI
Aug 11
LLMVisor: A Real-Time Latency Attribution Model for Multi-Tenant LLM Serving
arXiv:2608. 08382v1 Announce Type: new Abstract: As LLM inference shifts to multi-tenant GPU clusters, co-batching improves throughput but obscures per-tenant usage and limits control.
arXiv AI
Aug 11
MARA: Flow-Matching-Guided Multi-Agent Resource Allocation for Computational Resource Efficient Learning
arXiv:2608. 09130v1 Announce Type: cross Abstract: Allocating limited computation among concurrent learning tasks is difficult when each task must reach a target loss before a deadline but its required training effort is unknown.
arXiv Machine Learning
Aug 11
Unsupervised Point Cloud Registration with Self-Distillation
arXiv:2409. 07558v2 Announce Type: replace-cross Abstract: Rigid point cloud registration is a fundamental problem and highly relevant in robotics and autonomous driving.
arXiv AI
Aug 11
SR-OPSD: Self-Referenced On-Policy Self-Distillation
arXiv:2608. 09745v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, providing a useful complement to reinforcement learning with sparse outcome rewards.