Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
With the rapid development of large-scale pre-trained language models based on Transformer architectures, their high computational and memory costs have become a major obstacle to deployment, especial...
End-to-end multimodal driving has progressed rapidly by fusing camera and LiDAR streams. Existing pipelines remain fragile under asymmetric sensor degradation, where either an entire modality or only...
Transformer-based object trackers are renowned for their strong performance, yet dense token processing often leads to prohibitive computational cost, limiting real-time deployment on edge devices. Wh...
Search-augmented reasoning remains difficult for small language models. On-policy distillation (OPD) from trained teachers offers a promising direction, but suffers from two issues: (1) high-quality m...
LLM-as-judge is essential for evaluating open-ended text and steering post-training, yet improving the judge itself typically relies on expensive annotations, reward models, or distillation from stron...
Semantic identifiers (SIDs) represent entities as hierarchical token sequences for generative retrieval and recommendation. Residual-quantization tokenizers construct these sequences by selecting a co...
OpenAI’s new custom inference chip, Jalapeño, achieves industry-leading speed and efficiency in AI inference. It delivers faster, more power‑efficient performance with higher throughput and lower latency for modern models. The chip represents a significant hardware advancement for deploying AI workloads.
Prohibitive computational and environmental costs impede the scalable deployment of Large Language Models (LLMs). Traditional compression techniques (sparsity, quantization, low-rank approximations) a...
arXiv:2608.23144v1 Announce Type: cross Abstract: Low-bit weight quantization saves storage but leaves errors that degrade language-model quality. We introduce Activation-Weighted Seeded Residual Cod...
arXiv:2412.07264v2 Announce Type: replace-cross Abstract: Understanding complex animal behaviors hinges on deciphering the neural activity patterns within brain circuits, making the ability to foreca...
arXiv:2608.22830v1 Announce Type: new Abstract: Deploying LLMs for enterprise Text-to-SQL is bottlenecked less by the model than by what context reaches it: business logic spans thousands of tables,...
arXiv:2608.22788v1 Announce Type: new Abstract: Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning (RL) post-training, on-policy distillation (OP...
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
arXiv:2608.22595v1 Announce Type: new Abstract: We develop a new framework for flexible, nonlinear, and interpretable off-policy evaluation for infinite-horizon reinforcement learning. To handle larg...
arXiv:2608.22196v1 Announce Type: cross Abstract: While cascaded multi-talker ASR (MT-ASR) leverages state-of-the-art foundation models, its performance is often capped by speaker leakage during sepa...
arXiv:2608.22368v1 Announce Type: new Abstract: While linear attention is a compelling mechanism for high-resolution object detection due to its reduced cost for global token mixing, converting the S...
The paper revisits the impact of pruning on large language models (LLMs) during test-time scaling (TTS). While prior work found that structured pruning degrades reasoning performance, this study shows that unstructured pruning—removing only specific redundant weights—can actually improve TTS performance on reasoning benchmarks for models s1.1-7B and Qwen3-8B, sometimes surpassing the full-weight models. The authors also examine how different layer-wise sparsity allocation strategies affect these outcomes.
arXiv:2608.21754v1 Announce Type: new Abstract: Despite the success of data pruning (DP) in reducing training data sizes and improving downstream model performance in classification and segmentation...
arXiv:2608.23101v1 Announce Type: cross Abstract: Recent progress in the field of TinyML has demonstrated that low-power hardware based on microcontrollers can achieve bird species monitoring in real...
arXiv:2608.22389v1 Announce Type: cross Abstract: Regulation (EU) 2024/886 obliges European payment service providers to settle euro credit transfers in under ten seconds, around the clock. This remo...