Empowering Compact LLMs with Fusion of Layer-wise Exits for Recommendation

• URL: http://arxiv.org/abs/2608.17316v2
• Date: Thu, 27 Aug 2026 12:55:28 GMT
• Title: Empowering Compact LLMs with Fusion of Layer-wise Exits for Recommendation
• Abstract summary: Large language model-based recommender systems (LLM-RSs) have demonstrated remarkable capabilities, but are computationally unsustainable for many real-world applications.<n>We propose a discriminative framework that enhances compact LLMs while retaining scalable full-corpus ranking.<n>Experiments on three real-world datasets with Qwen 3 1.7B and Llama 3.2 3B show that FLEXRec achieves state-of-the-art accuracy while remaining highly efficient.
• Score: 59.216721553953
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model-based recommender systems (LLM-RSs) have demonstrated remarkable capabilities, but are computationally unsustainable for many real-world applications. Compact LLMs offer a practical alternative, yet their reduced capacity often requires reasoning or knowledge distillation methods that increase latency or depend on larger models. Combined with autoregressive generation, these approaches face severe scalability bottlenecks. In contrast, discriminative LLM-RSs enable efficient full-corpus ranking through embedding similarity, but compact backbones remain limited in expressiveness and structural adaptivity. We propose the Fusion of Layer-wise Exits for Sequential Recommendation (FLEXRec), a discriminative framework that enhances compact LLMs while retaining scalable full-corpus ranking. FLEXRec inserts prediction heads (i.e., exits) at multiple transformer layers and adaptively fuses their score distributions. An adaptive continuous router (AC-Router) dynamically selects both the number and identity of exits for each user sequence, while a novel target-k hinge loss regulates routing sparsity. Experiments on three real-world datasets with Qwen 3 1.7B and Llama 3.2 3B show that FLEXRec achieves state-of-the-art accuracy among competing methods while remaining highly efficient. Code: https://github.com/xurong-liang/FLEXRec

Related papers

• Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models [11.628969213956502]
  We show that expert-choice routing is a better fit for Diffusion language models than token-choice routing.<n>We introduce timestep-dependent expert capacity, which varies expert allocation according to the denoising step.<n>Results establish EC routing as a superior paradigm for DLM MoE models.
  arXiv  Detail & Related papers  (2026-04-02T05:01:36Z)
• AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization [84.25316984309725]
  Integration of dynamic, sparse structures with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs)<n>Despite minimal increases in computational load, the computation latency often skyrockets, leading to decoding speeds slowing by over 2.5 times.<n>AdaFuse is a framework built on a tight co-design between the algorithm and the underlying hardware system to enable efficient dynamic adapter execution.
  arXiv  Detail & Related papers  (2026-03-12T12:46:42Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs [28.752042722391934]
  Sequential recommendation (SR) aims to capture users' dynamic interests and sequential patterns based on their historical interactions.<n>MME-SID integrates multimodal embeddings and quantized embeddings to mitigate embedding collapse.<n>Extensive experiments on three public datasets validate the superior performance of MME-SID.
  arXiv  Detail & Related papers  (2025-09-02T07:02:29Z)
• ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism [9.93378263858092]
  Multimodal large language models (MLLMs) handle images, videos, and audio by incorporating feature extractors and projection modules.<n>Current tightly coupled serving architectures struggle to distinguish between mixed request types.<n>We introduce Elastic Multimodal Parallelism (EMP), a new serving paradigm that elastically adapts to resource heterogeneity.
  arXiv  Detail & Related papers  (2025-07-14T08:53:48Z)
• EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices [7.596547050649462]
  This paper introduces EdgeLoRA, an efficient system for serving Large Language Models (LLMs) on edge devices in multi-tenant environments.<n> EdgeLoRA incorporates three key innovations: (1) an adaptive adapter selection mechanism to streamline the adapter configuration process; (2) heterogeneous memory management, leveraging intelligent adapter caching and pooling to mitigate memory operation overhead; and (3) batch LoRA inference, enabling efficient batch processing to significantly reduce computational latency.
  arXiv  Detail & Related papers  (2025-07-02T07:47:28Z)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [60.407727995313074]
  We introduce adaptive parallel decoding (APD), a novel method that dynamically adjusts the number of tokens sampled in parallel.<n>APD provides markedly higher throughput with minimal quality degradations on downstream benchmarks.
  arXiv  Detail & Related papers  (2025-05-31T06:10:10Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator [5.985414012866983]
  Large language model (LLM) pruning with fixed N:M structured sparsity limits the expressivity of the sparse model.<n>We present a flexible layer-wise outlier-density-aware N:M sparsity (FLOW) selection method.<n>We then introduce a flexible, low-overhead digital compute-in-memory architecture (FlexCiM)
  arXiv  Detail & Related papers  (2025-04-19T17:47:01Z)
• LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation [57.49045064294086]
  Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity.<n>We introduce LLMEmb, a novel method leveraging LLM to generate item embeddings that enhance Sequential Recommender Systems (SRS) performance.
  arXiv  Detail & Related papers  (2024-09-30T03:59:06Z)
• MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines [28.18421624702502]
  We introduce MobiZO, a resource-efficient fine-tuning framework for Large Language Models (LLMs) specifically designed for edge devices.<n>We show that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy.<n> Experiments demonstrate that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy.
  arXiv  Detail & Related papers  (2024-09-23T20:14:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.