Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in contextual grounding than earlier ones. A simple and effective remedy is prompt repetition -- just appending a second copy of prompt before generation can redistribute grounding across positions and improve reasoning performance.
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgetting, with on-policy self-distillation emerging as a particularly attractive approach.
3D plant phenotyping is notoriously known to be procedure-complicated and of low throughput due to the extensive multi-view imaging, the fragile 3D reconstruction pipeline, and the additional cost from reconstructed geometry to phenotypic extraction. These limitations are further amplified in low-cost data acquisition, where smartphone videos or sparsely sampled multi-view images provide limited view overlap and self-occlusion.
Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging. Existing expert-pruning methods typically rely on a single aggregated importance score, which can bias the retained set toward experts favored by dominant calibration patterns.
arXiv:2607. 01170v1 Announce Type: cross Abstract: Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they are slow at inference: an autoregressive (AR) decoder spends one sequential forward pass per reasoning token, and the reasoning trace far exceeds the ranking it produces.
arXiv:2607. 01083v1 Announce Type: cross Abstract: High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates.
arXiv:2607. 01125v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables fine-tuning large language models when backpropagation is unavailable or memory-prohibitive, but existing methods often perturb full model weights or randomly constructed low-dimensional subspaces, yielding high-variance estimates and limited performance.
arXiv:2607. 00734v1 Announce Type: cross Abstract: Table Structure Recognition (TSR) aims to recover the row and column layout of tables from document images, a key step in document understanding pipelines.
arXiv:2607. 00004v1 Announce Type: cross Abstract: While advanced foundation models like ModernBERT significantly outperform older architectures in dense retrieval, they surprisingly lag behind the aging BERT-base baseline in learned sparse retrieval (LSR).
arXiv:2607. 00363v1 Announce Type: cross Abstract: Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage.
arXiv:2607. 00927v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption.
arXiv:2503. 24075v4 Announce Type: replace-cross Abstract: Low-rank optimization problems with sparse simplex constraints involve variables that must satisfy nonnegativity, sparsity, and sum-to-1 conditions, making their optimization particularly challenging due to the interplay between low-rank structures and constraints.
arXiv:2603. 00198v2 Announce Type: replace-cross Abstract: Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as token pruning.
arXiv:2607. 01164v1 Announce Type: new Abstract: Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying with a reduced memory footprint.
arXiv:2604. 25421v2 Announce Type: replace-cross Abstract: Federated fine-tuning provides a practical route to adapt large language models (LLMs) on edge devices without centralizing private data, yet in mobile deployments the training wall-clock is often bottlenecked by straggler-limited uplink communication under heterogeneous bandwidth and intermittent participation.
arXiv:2607. 01065v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) with extended context windows is increasingly constrained by the linear growth of Key-Value (KV) cache memory.
arXiv:2607. 01115v1 Announce Type: cross Abstract: University stakeholders often face difficulties in accessing timely and reliable information, especially in developing countries, where there are very few intelligent support systems.
arXiv:2607. 00692v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate tool results, files, plans, and user constraints that are too structured to be treated as a disposable text suffix.
arXiv:2607. 00553v1 Announce Type: cross Abstract: Lightweight machine learning models are increasingly proposed for intrusion detection in Industrial Internet of Things (IIoT) networks due to their suitability for resource-constrained edge deployment.
arXiv:2507. 10540v3 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has created a diverse landscape of models, each excelling at different tasks.