Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2605.16861v2 Announce Type: replace-cross Abstract: Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient docume...
arXiv:2508.01684v2 Announce Type: replace Abstract: While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains...
arXiv:2608.28730v1 Announce Type: cross Abstract: Latest JPEG restoration systems achieve strong quality with large models, yet often remain too slow and expensive for efficient on-device deployment....
arXiv:2608.29208v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models, built upon Vision-Language Models (VLMs), have significantly enhanced robotic capabilities by leveraging interne...
arXiv:2603.02263v3 Announce Type: replace-cross Abstract: World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such...
The paper introduces ACTD, an Anchor-Based Cross-Tokenizer Distillation method that aligns vocabularies and sequences to transfer reasoning capabilities from large language models to smaller students. It uses a novel anchor loss with residual regularization to reduce alignment noise and extends the approach to multiple teachers. Experiments on five reasoning benchmarks with three teachers show state‑of‑the‑art results, with the multi‑teacher variant outperforming existing baselines.
The paper introduces GRKV, a training‑free method for compressing the key‑value cache in long‑context large language models. GRKV uses ridge‑regression to redistribute information from evicted tokens to retained ones, aiming to minimize the difference between compressed‑cache and full‑cache attention outputs. Experiments on LongBench and RULER show that GRKV improves overall performance with minimal overhead compared to other merging methods.
Post‑training quantization of large language models reduces memory usage but can alter social biases in ways that aggregate metrics miss. In a large‑scale study of 50 quantized models on PostTrainingBiasBench, the authors discovered a phenomenon called quantization‑induced bias flipping, where up to 21% of responses switch from biased to unbiased or vice versa, especially for uncertain predictions and stronger quantization (4‑bit vs 8‑bit). These flips lead to asymmetric impacts across demographic groups, with some groups experiencing up to an 18.6% worsening of bias while others improve by 14.1%, resulting in misleadingly neutral overall scores.
arXiv:2608.30163v1 Announce Type: cross Abstract: Real-world knowledge resides in multimodal documents, necessitating retrieval-augmented generation (RAG) for accurate question answering. However, ex...
arXiv:2608.31053v1 Announce Type: new Abstract: Diffusion models have achieved strong results in high-fidelity image synthesis, but their iterative sampling process makes large-scale generation compu...
SpanCalib-VLM is a hybrid system for detecting hallucinated text spans in Vision‑Language Models. It combines a multimodal sequence tagger (XLM‑RoBERTa‑Large + SigLIP) with a fine‑tuned generative VLM (Qwen3.5‑4B‑SHROOM‑SFT) and uses a Union‑Calibrated Fusion strategy to re‑score candidate spans. On the SHROOM‑Visions English evaluation split, the ensemble achieves a Pearson calibration correlation of 0.41, an overall IoU of 0.39, a clean‑response IoU of 0.91, and a detection accuracy of 70.7%.
Context-Aware Interleaved Batching for WhisperX proposes a new batching strategy that combines WhisperX’s fast intra-audio batching with Whisper’s sequential context retention. By using voice activity detection (VAD) to define segment boundaries, the algorithm stabilizes Whisper’s text conditioning and preserves continuous historical context across batched audio segments. Experiments on long‑form audio benchmarks show reduced Word Error Rate and improved proper noun transcription while maintaining high‑throughput inference speeds.
arXiv:2608.29263v1 Announce Type: new Abstract: Large Language Models (LLMs) often suffer from hallucination and struggle with complex reasoning tasks requiring multi-hop domain knowledge. While inte...
arXiv:2409.11018v3 Announce Type: replace Abstract: The LiDAR 3D object detector that balances accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many ex...
arXiv:2604.13287v2 Announce Type: replace Abstract: Weight pruning is a common technique for compressing large neural networks. We focus on the challenging post-training one-shot setting, where a pre...
arXiv:2608.30692v1 Announce Type: new Abstract: Video world models are increasingly used as simulators, yet visual fidelity alone does not show that a model maintains the hidden state of the world. W...
arXiv:2602.08136v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic...
arXiv:2608.29897v1 Announce Type: new Abstract: Long-horizon agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active s...
arXiv:2608.30870v1 Announce Type: new Abstract: Semantic segmentation in 3D Gaussian Splatting (3DGS) is crucial for advancing 3D scene understanding. Existing methods predominantly rely on feature d...
arXiv:2608.29057v1 Announce Type: new Abstract: Koopman autoencoders (KAEs) seek a higher-dimensional latent representation in which nonlinear dynamics evolve linearly. However, many interesting syst...