Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2510. 09711v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches.
arXiv:2602. 20217v2 Announce Type: replace-cross Abstract: Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in long-context scenarios.
arXiv:2602. 06960v3 Announce Type: replace-cross Abstract: Large reasoning models achieve strong performance by scaling inference-time chain-of-thought, but this paradigm suffers from quadratic cost, context length limits, and degraded reasoning due to lost-in-the-middle effects.
arXiv:2605. 18629v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features.
arXiv:2606. 03532v1 Announce Type: cross Abstract: Self on-policy distillation trains a student policy against a teacher derived from its own parameter history, yet the teacher's update schedule -- which governs the \emph{temporal coupling} between teacher and student -- has not been systematically studied as a stability variable.
arXiv:2603. 20508v2 Announce Type: replace-cross Abstract: Reasoning language models (RLMs) and the intermediate chains of thought they emit play an increasingly central role in multi-agent setups such as inter-model monitoring or distillation into smaller models.
arXiv:2606. 03939v1 Announce Type: cross Abstract: Federated Learning (FL) of foundation and edge models increasingly targets deployments where client data distributions drift over time, yet existing forgetting-mitigation methods assume each client's distribution is stationary.
arXiv:2606. 03257v1 Announce Type: cross Abstract: Spiking Vision Transformer (SViT) models are promising low-power ViT models for solving vision-based tasks with state-of-the-art performance.
arXiv:2511. 17126v4 Announce Type: replace-cross Abstract: Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demonstrating strong capability in handling diverse unknown optical degradations.
arXiv:2606. 02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation.
arXiv:2512. 13996v3 Announce Type: replace Abstract: Sparse Mixture-of-Experts architectures are essential for scaling model capacity efficiently, yet the standard Top-$k$ routing imposes a rigid sparsity pattern that ignores the intrinsic variance in token difficulty and layer-specific computational needs.
arXiv:2606. 02951v1 Announce Type: cross Abstract: Deploying language-driven agents in robotics requires evaluations that reflect real-world task demands: natural-language instructions with reproducible outcomes.
arXiv:2606. 03569v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference.
arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.
arXiv:2606. 02955v1 Announce Type: cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together.
arXiv:2512. 09106v4 Announce Type: replace Abstract: Diffusion (Large) Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks, while holding the promise of being more efficient during inference.
arXiv:2606. 03645v1 Announce Type: cross Abstract: Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output.
arXiv:2606. 03620v1 Announce Type: cross Abstract: Self-distilled policy optimization (SDPO) has become a popular paradigm for LLM post-training, where a model learns from its own predictions conditioned on privileged information.
arXiv:2606. 02842v1 Announce Type: new Abstract: Multimodal spatial reasoning often relies on long chains of intermediate textual and visual thoughts, where accumulating visual tokens and dense cross-modal attention incur substantial computation and memory overhead.
Federated Learning (FL) of foundation and edge models increasingly targets deployments where client data distributions drift over time, yet existing forgetting-mitigation methods assume each client's distribution is stationary. Flashback, the strongest recent FL method against cross-client (spatial) forgetting, uses monotonically accumulating per-class label counts as a knowledge proxy; this proxy becomes miscalibrated under temporal distribution shift and anchors the global model to an outdated class balance.