heterogeneous-models

Tag

Cards List
#heterogeneous-models

AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows

arXiv cs.AI · 17h ago Cached

AgentRouter is a lightweight classifier for routing steps in agentic workflows to different model tiers, achieving 72% cost reduction with minimal quality degradation compared to frontier-only models.

0 favorites 0 likes
#heterogeneous-models

LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification

arXiv cs.CL · 2026-09-14 Cached

The paper proposes DualMLC, a dual-branch framework that combines autoregressive and bidirectional language models for large-scale multi-label text classification, achieving state-of-the-art results on benchmarks.

0 favorites 0 likes
#heterogeneous-models

Dual-Cache Latent Space Communication between Heterogeneous Language Models

arXiv cs.AI · 2026-08-24 Cached

The paper introduces XKV, a method for efficient latent space communication between heterogeneous language models in multi-agent systems, improving accuracy and speed over existing text and cache-based protocols.

0 favorites 0 likes
#heterogeneous-models

Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models

arXiv cs.CL · 2026-08-03 Cached

This paper introduces Mixture-of-Translators (MoT), a framework for translating KV caches across heterogeneous LLMs, enabling cache reuse between different architectures. Experiments show preserved QA performance and long-context quality across Qwen2.5, GPT-2, and OPT models.

0 favorites 0 likes
#heterogeneous-models

Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems

arXiv cs.LG · 2026-07-10 Cached

Introduces Collate, a training framework for collaborative neural network learning that handles heterogeneous edge devices with latency constraints, achieving accuracy improvements with minimal overhead.

0 favorites 0 likes
← Back to home

Submit Feedback