Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2601. 22709v5 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss.
arXiv:2603. 05121v2 Announce Type: replace-cross Abstract: Speech Large Language Models route speech encoder representations into an LLM decoder that typically accounts for over 90% of total parameters.
arXiv:2606. 27784v1 Announce Type: cross Abstract: The existence of adversarial attacks is often attributed to the presence of non-robust features in neural networks.
arXiv:2606. 27527v1 Announce Type: cross Abstract: Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored.
arXiv:2606. 27743v1 Announce Type: cross Abstract: Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment.
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
arXiv:2604. 00757v2 Announce Type: replace-cross Abstract: Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens.
Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in long-horizon tasks. The concern that increasing context length degrades model capabilities, known as context rot, has become a central issue for these applications.
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.
Modern LLM deployments routinely compress models and raise sampling temperature to reduce cost, latency, or repetition, yet safety evaluations usually treat these choices as fixed implementation details. This leaves a practical uncertainty: does a model that is safe at FP16 and greedy decoding remain safe after it is quantized and sampled stochastically, or do the two deployment knobs amplify one another?
Open-vocabulary 3D semantic Gaussian field learning relies on multi-view 2D supervision, whose semantic targets and spatial assignments are often unreliable. Across varying viewpoints, view-dependent features cause semantic identity drift, while propagated tracker masks introduce boundary leakage and identity switches.
arXiv:2606. 26769v1 Announce Type: new Abstract: The adoption of powerful diffusion models is hindered by their significant inference latency.
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. 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. 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. 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. 26373v1 Announce Type: cross Abstract: Dense embeddings power semantic search and retrieval-augmented generation, but embedding-inversion attacks can reconstruct source text from a vector: when a vector database leaks, the documents behind it leak too.
arXiv:2606. 26123v1 Announce Type: cross Abstract: Ultra-low latency and high throughput are required for Virtual Reality (VR) services in 6G networks, which presents critical challenges for Software-Defined Radio Access Networks (SD-RANs) dynamic resource management.
arXiv:2606. 26749v1 Announce Type: new Abstract: Neural Collapse predicts that balanced one-hot classification pushes model representations to be equally far from each other; a symmetric configuration that depends only on the output label and ignores any semantic similarity in the inputs.
arXiv:2606. 26762v1 Announce Type: cross Abstract: Streaming video understanding (SVU) must answer queries that arrive asynchronously while visual tokens stream continuously under strict GPU-memory and query-time latency budgets.