Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2609.37017v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) increasingly use latent collaboration to avoid the information loss and repeated encoding-decoding overhead of natu...
arXiv:2609.37837v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly el...
arXiv:2609.38106v1 Announce Type: cross Abstract: Speech-LLMs are expensive to run, making compression important for real-world deployment. However, compressed models are usually selected using aggre...
arXiv:2609.36407v1 Announce Type: new Abstract: Cross-resolution knowledge distillation aims to improve low-magnification whole- slide analysis by transferring high-magnification representations, yet...
arXiv:2609.36826v1 Announce Type: new Abstract: Video generation models have demonstrated emerging zero-shot capabilities for visual reasoning, perception, and other vision tasks. However, diffusion-...
arXiv:2609.36866v1 Announce Type: new Abstract: Inter-modality MRI translation aims to synthesize missing MRI modalities from available acquisitions, reducing the need for additional scanning while p...
arXiv:2609.36929v1 Announce Type: new Abstract: Recent event-based depth estimation methods successfully transfer geometric priors from vision foundation models via cross-modal distillation. However,...
arXiv:2609.36916v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur high inference latency from long visual token sequences. Existing pruning methods commonly use attention...
arXiv:2609.38114v1 Announce Type: new Abstract: Autoregressive video diffusion enables interactive streaming generation, but suffers from error accumulation over long rollouts. Self-rollout training...
arXiv:2609.38123v1 Announce Type: new Abstract: World simulation is inherently multisensory, demanding synchronized visual and acoustic dynamics in real time. Yet prevailing interactive world models...
arXiv:2609.36520v1 Announce Type: cross Abstract: RGB-only end-to-end visual navigation policies remain vulnerable to collisions in real-world dynamic environments, motivating a dedicated safety laye...
arXiv:2609.38054v1 Announce Type: cross Abstract: We present Pow3R-SLAM, a real-time RGB-D simultaneous localization and mapping (SLAM) system that uses Pow3R for tracking and mapping. Inspired by MA...
arXiv:2609.38059v1 Announce Type: cross Abstract: Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a sca...
arXiv:2609.33384v2 Announce Type: replace Abstract: Quantization errors in video diffusion transformers can be amplified or attenuated by subsequent denoising updates, making local reconstruction err...
arXiv:2609.34581v2 Announce Type: replace Abstract: Temporal video grounding is a key capability of advanced Multimodal Large Language Models (MLLMs) for the thorough understanding of video events, w...
arXiv:2609.34658v2 Announce Type: replace Abstract: Reward-specialized post-training produces strong experts for flow-based generative models, while multi-teacher on-policy distillation (OPD) consoli...
arXiv:2606.21030v2 Announce Type: replace-cross Abstract: Diffusion-based image compression has achieved strong perceptual quality at ultra-low bitrates. However, existing codecs are often tied to sp...
arXiv:2609.38093v1 Announce Type: new Abstract: Risk aversion in resources could prevent misaligned AI agents from causing catastrophic harm. Misaligned but risk-averse agents would tend to favor saf...
arXiv:2609.36326v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) hands the user's query to whoever hosts the corpus. We propose PILLAR, a Privacy-Preserving RAG (PPRAG) system bas...
arXiv:2609.36652v1 Announce Type: new Abstract: Open-ended generation lacks canonical answers, making pointwise rewards difficult to calibrate for group-based reinforcement learning. Directly ranking...