Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2609.24259v1 Announce Type: new Abstract: The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over...
arXiv:2609.24298v1 Announce Type: new Abstract: What limits KV-cache compression at extreme bit-rates? We argue that it is not the choice of compression scheme, but how its budget is allocated across...
arXiv:2609.24322v1 Announce Type: new Abstract: We show that a quantized model that keeps its classification accuracy still changes $14$ to $46\%$ of its top-1 retrieval results, and that aggregate r...
arXiv:2609.24417v1 Announce Type: new Abstract: Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are...
arXiv:2609.24485v1 Announce Type: new Abstract: Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction oft...
arXiv:2609.24538v1 Announce Type: new Abstract: Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far f...
arXiv:2609.24646v1 Announce Type: new Abstract: On-policy self-distillation fine-tuning (SDFT) learns new skills from demonstrations while reducing forgetting, but it always distils toward the full d...
arXiv:2609.24691v1 Announce Type: new Abstract: Latent diffusion models now dominate medical image generation, and every such pipeline rests on a \emph{tokenizer} that compresses images into the late...
arXiv:2609.24698v1 Announce Type: new Abstract: Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which foll...
arXiv:2507.22920v2 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data int...
arXiv:2510.03095v4 Announce Type: replace Abstract: Diffusion- and flow-based generative models have recently demonstrated strong performance in protein backbone generation tasks, offering unpreceden...
arXiv:2512.07624v2 Announce Type: replace Abstract: Process Model Forecasting (PMF) aims to predict how the control-flow structure of a process evolves over time by modeling the temporal dynamics of...
arXiv:2604.11508v3 Announce Type: replace Abstract: Fine-tuning a pretrained classifier leaves some samples reliably learned and others cycling between correct and incorrect. Curriculum learning, dat...
The paper introduces a hybrid attention model that learns a unified time‑aware patch representation for irregular multivariate time series (IMTS) forecasting. It employs a time‑aware patch encoding to embed variable‑length intra‑patch timestamps, a time bias attention mechanism to adjust for temporal misalignment and asynchronous cross‑channel dependencies, and a hybrid causal mask on a decoder‑only Transformer to balance historical context with autoregressive forecasting. The authors also curate VersaTSA, a 30 B‑observation dataset preserving native sampling sparsity, and demonstrate state‑of‑the‑art zero‑shot performance on three IMTS benchmarks while remaining competitive on regular MTS tasks.
arXiv:2609.23697v1 Announce Type: cross Abstract: Multi-teacher on-policy distillation allows a student to learn from complementary specialists on its own trajectories. Domain-routed approaches, howe...
Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world m...
Recent foundation models are moving toward native multimodal Vision-Language Models (VLMs), making VLMs a central form of next-generation foundation models. However, their large language backbones mak...
LiDAR point clouds acquired in underground environments exhibit severe geometric incompleteness due to occlusions and limited sensor viewpoints, making reliable point cloud completion challenging with...
Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes substantial performance degradation. We...