Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 01590v1 Announce Type: new Abstract: Developing high-performance kernels for Neural Processing Units (NPUs) is a critical industry bottleneck, requiring developers to manually navigate implicit hardware constraints and strict memory hierarchies.
arXiv:2606. 13501v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving.
arXiv:2607. 02097v1 Announce Type: cross Abstract: Large kernel depthwise convolutions achieve strong performance but suffer from significant degradation as kernel size grows due to irregular memory access from gather-based computation; while Large Kernel Acceleration (LKA) helps on small feature maps, it becomes counterproductive on large feature maps, even slower than non-accelerated implementations.
arXiv:2607. 01792v1 Announce Type: cross Abstract: 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.
arXiv:2607. 01678v1 Announce Type: new Abstract: Communication increasingly dominates the cost of Large Language Model (LLM) pre-training, especially under data-parallel and sharded training schemes, where gradient synchronization and parameter reconstruction overhead increase with model size and system scale.
arXiv:2512. 02657v2 Announce Type: replace-cross Abstract: Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations arise over time.
arXiv:2510. 04391v5 Announce Type: replace Abstract: Mental imagery vividness is a stable individual trait, yet whether imagined scenarios share relational structure across human and synthetic large language model (LLM) populations remains unknown.
arXiv:2607. 02460v1 Announce Type: cross Abstract: Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain.
arXiv:2607. 02371v1 Announce Type: cross Abstract: Over 285 million people worldwide live with a visual impairment, for whom everyday tasks such as avoiding obstacles, locating personal belongings, recognizing familiar faces, or handling cash remain persistent obstacles to personal autonomy.
arXiv:2607. 02119v1 Announce Type: cross Abstract: While Large Multimodal Models excel in comprehension, high-throughput inference engines lack native support for multimodal generation.
arXiv:2607. 01272v1 Announce Type: cross Abstract: Deploying 3D point cloud analysis in privacy-sensitive, resource-constrained settings faces two barriers: data cannot be centralized, and models must run on limited edge hardware.
arXiv:2607. 02509v1 Announce Type: new Abstract: Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications.
arXiv:2607. 02303v1 Announce Type: new Abstract: Linear-attention and state-space language models compress the prefix into a fixed-size recurrent state, yielding O(1) memory at the cost of a lossy exact memory: when many key--value associations compete, earlier facts are overwritten and needle recall degrades.
arXiv:2607. 02484v1 Announce Type: cross Abstract: Visual token pruning is a crucial strategy for accelerating VLMs by compressing redundant image patches, yet existing methods often fail to preserve critical cues under dense instructions and fine-grained queries.
arXiv:2607. 01844v1 Announce Type: cross Abstract: This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models.
arXiv:2607. 02461v1 Announce Type: cross Abstract: Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive.
arXiv:2607. 01831v1 Announce Type: cross Abstract: Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems.
arXiv:2509. 25136v3 Announce Type: replace Abstract: Activation-aware low-rank factorization techniques yield strong compression results but are generally confined to linear layers, while existing whitening-based theory typically makes an implicit full-rank assumption on activations.
arXiv:2607. 02413v1 Announce Type: cross Abstract: Here we describe the quantum gas analysis and inference (Q-GAIN) Python package, which enables rapid deployment of machine learning (ML) and physics-informed analysis techniques for cold-atom experiments.
arXiv:2512. 07843v2 Announce Type: replace-cross Abstract: Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial latency, motivating parallelization of the generation process.