arXiv AI
Jul 7
Separating Representation from Reconstruction Enables Scalable Text Encoders
arXiv:2607. 04011v1 Announce Type: cross Abstract: While decoders have rapidly scaled, encoders have remained largely unchanged since BERT.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv AI
Jul 7
From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips
arXiv:2603. 22770v2 Announce Type: replace-cross Abstract: The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors.
arXiv AI
Jul 7
Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering
arXiv:2607. 04079v1 Announce Type: cross Abstract: Recent Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on 2D question answering tasks.
arXiv Machine Learning
Jul 7
Context-Constrained Transfer Learning for Tabular Foundation Models via Data Distillation
arXiv:2607. 04809v1 Announce Type: cross Abstract: Tabular Foundation Models (TFMs) have demonstrated strong empirical performance as black-box inference engines through in-context learning.
arXiv Machine Learning
Jul 7
SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation
arXiv:2607. 04306v1 Announce Type: new Abstract: Distilling a fine-tuned teacher into a LoRA-adapted student is a standard recipe for parameter-efficient compression, but output-level KD does not explicitly control which rank-$r$ weight subspace the adapter occupies.
arXiv Machine Learning
Jul 7
Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
arXiv:2603. 14830v3 Announce Type: replace Abstract: Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data storage.
arXiv AI
Jul 7
Order-based Causal Discovery for Multistage Processes
arXiv:2607. 03971v1 Announce Type: cross Abstract: Causality has become an increasingly important tool for gaining a deeper understanding of complex systems.
arXiv AI
Jul 7
Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs
arXiv:2607. 04371v1 Announce Type: new Abstract: We present Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super optimized for interactive deployment.
arXiv AI
Jul 7
Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective
arXiv:2607. 03784v1 Announce Type: cross Abstract: While prior studies have successfully compressed vision Transformers (ViTs) through various pruning techniques, most have concentrated on width pruning to achieve significant reductions in model size.
arXiv Machine Learning
Jul 7
Toward Efficient Uncertainty in LLMs through Evidential Knowledge Distillation
arXiv:2507. 18366v2 Announce Type: replace Abstract: Accurate uncertainty quantification remains a key challenge for standard LLMs, prompting the adoption of Bayesian and ensemble-based methods.
arXiv AI
Jul 7
FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion
arXiv:2602. 05305v3 Announce Type: replace-cross Abstract: Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models.
arXiv AI
Jul 7
From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving
arXiv:2607. 02574v1 Announce Type: cross Abstract: The key-value (KV) cache has become a first-order memory object in LLM serving rather than a temporary per-request tensor.
arXiv Machine Learning
Jul 7
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
arXiv:2607. 05061v1 Announce Type: new Abstract: Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length.
arXiv Machine Learning
Jul 7
Effective Distillation to Hybrid xLSTM Architectures
arXiv:2603. 15590v2 Announce Type: replace Abstract: There have been numerous attempts to distill quadratic attention-based large language models (LLMs) into sub-quadratic linearized architectures.
arXiv AI
Jul 7
Conflict-Based Lazy Search for Fast Multi-Manipulator Planning
arXiv:2607. 04124v1 Announce Type: cross Abstract: Employing multiple manipulators can boost efficiency and accomplish tasks that a single manipulator cannot do.
arXiv AI
Jul 7
Panorama: Fast-Track Nearest Neighbors
arXiv:2510. 00566v4 Announce Type: replace-cross Abstract: Approximate Nearest-Neighbor Search (ANNS) pipelines for high-dimensional neural embeddings spend the bulk of their query time in candidate verification, making it the primary bottleneck in the search process.
arXiv AI
Jul 7
GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
arXiv:2607. 05369v1 Announce Type: cross Abstract: For robots to work reliably in commercial and industrial applications, can recent advances in agentic coding systems combine interpretable robot programming with the open-world adaptability of model-free policies?
arXiv AI
Jul 7
RADIO1D: Elastic Representations for Condensed Vision Modeling
arXiv:2607. 03624v1 Announce Type: cross Abstract: This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features.
arXiv AI
Jul 7
Online Linear Programming for Multi-Objective Routing in LLM Serving
arXiv:2607. 03948v1 Announce Type: new Abstract: We study the online routing problem in large language model serving, where requests arrive sequentially and must be dispatched to parallel decode workers under tight batch-size and KV-cache constraints.
arXiv AI
Jul 7
ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
arXiv:2601. 07475v2 Announce Type: replace-cross Abstract: The emergence of fine-grained numerical formats like NVFP4 presents new opportunities for efficient Large Language Model (LLM) inference.