Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2603. 19864v2 Announce Type: replace Abstract: Penetration testing, the practice of simulating cyberattacks to identify vulnerabilities, is a complex sequential decision-making task that is inherently partially observable and features large action spaces.
arXiv:2606. 27294v1 Announce Type: cross Abstract: Analog hardware platforms such as coupled oscillators and Analog Ising Machines naturally solve differential equations at a fraction of the energy cost of digital computation, making them attractive for low-power generative modeling, yet a fundamental mismatch exists: modern generative models assume flexible, software-defined dynamics, whereas analog hardware imposes fixed, physics-determined differential equations with limited approximation capacity.
arXiv:2606. 26881v1 Announce Type: cross Abstract: We introduce an accelerated Langevin-based sampling method that is based on two complementary devices: \emph{SamAdams} adaptive timestepping, which automatically shrinks the effective integration step in stiff regions of phase space using a relaxed stiffness monitor, and \emph{position-adaptive Langevin} (PAL) dynamics, which concentrates friction along the local force direction while preserving the canonical distribution as the exact invariant measure.
arXiv:2606. 26154v1 Announce Type: cross Abstract: Autonomous microrobots navigating biological vasculature could enable targeted drug delivery and thrombolysis, yet training control policies for realistic environments remains an open challenge.
arXiv:2606. 26120v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms.
arXiv:2606. 26822v1 Announce Type: new Abstract: Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally constrained by communication bottlenecks, device heterogeneity, and the challenges of training under statistically non-IID data.
arXiv:2606. 26666v1 Announce Type: new Abstract: Autoregressive large language model (LLM) serving is increasingly limited by key-value (KV) cache movement rather than dense matrix multiplication.
arXiv:2606. 26744v1 Announce Type: new Abstract: We present HyperDFlash, a block-parallel speculative decoding framework tailored to the novel multi-hyper-connection (MHC) architecture proposed by DeepSeek-V4.
arXiv:2606. 26488v1 Announce Type: new Abstract: Recursive reasoning models can solve complex structured tasks with only a few million parameters by repeatedly updating a latent state.
arXiv:2606. 26453v1 Announce Type: new Abstract: We present KernelPro, a closed-loop multi-agent system that automatically generates, profiles, and iteratively optimizes GPU kernel code by integrating large language model (LLM) code generation with hardware profiler feedback and pluggable bottleneck detection tools.
arXiv:2603. 11625v2 Announce Type: replace-cross Abstract: While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies.
arXiv:2606. 27161v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introduces substantial computational overhead.
arXiv:2606. 27321v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have become a leading tool for interpreting the representations of vision foundation models, decomposing their polysemantic activations into a larger set of sparse, more monosemantic features.
arXiv:2502. 18966v2 Announce Type: replace Abstract: General chemical reaction conditions that achieve consistently high performance across multiple substrates are important for practical applications such as library synthesis and high-throughput experimentation.
arXiv:2606. 26620v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features.
arXiv:2606. 26875v1 Announce Type: cross Abstract: Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling and decoding stages.
arXiv:2606. 20869v2 Announce Type: replace-cross Abstract: We present a holistic methodology for artificial intelligence algorithm and accelerator co-design, co-search, and co-generation (A3C3), which jointly optimizes neural network architectures and their hardware implementations to address the inefficiencies of traditional top-down AI system design flows.
arXiv:2512. 02652v2 Announce Type: replace-cross Abstract: Existing methods for expressive music performance rendering, a conditional generation task that aims to generate a human-like performance from a symbolic score, rely on supervised learning over small labeled datasets, which limits scaling of both data volume and model size, despite the availability of vast unlabeled music, as in vision and language.
arXiv:2606. 26442v1 Announce Type: cross Abstract: We present AXLE (Axiom Lean Engine), a cloud service for Lean 4 proof manipulation, extraction, and verification.
arXiv:2603. 05310v3 Announce Type: replace-cross Abstract: While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural compression.