Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608.20497v1 Announce Type: new Abstract: Deploying high-accuracy neural networks on resource-constrained edge devices remains challenging, as existing approaches treat training, compression, a...
arXiv:2511.17886v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder ef...
arXiv:2608.20554v1 Announce Type: cross Abstract: The critical failure modes in deployed large language models (LLMs) are cross-dimensional: a model can score 99.3 in safety alignment while refusing...
ForeTime‑VLA is a causal vision‑language‑action policy that distills future‑aware representations from a frozen Fast‑WAM teacher, enabling it to anticipate contact events during conveyor‑belt manipulation. The method compresses current and future video latents into a 64‑dimensional target, uses an eight‑frame history encoder to predict this target along with manipulation phase and time‑to‑transition, and conditions a VLM prefix on future tokens and phase. On a deduplicated conveyor‑belt dataset, ForeTime‑VLA reduces test MAE by 2.63% and L2 by 3.02%, while real‑robot experiments show significantly higher grasp success rates compared to the next‑best reference. whyItMatters":"The approach demonstrates that distilling future‑token knowledge from a world‑action model can improve dynamic manipulation performance without the computational cost of running the teacher at inference time."
arXiv:2608.20375v1 Announce Type: new Abstract: Tree-based speculative decoding raises the mean accepted tokens of standard speculative decoding by verifying multiple draft paths, and existing tree b...
The paper identifies a specific issue in supervised fine‑tuning (SFT) of large language models called factual access failure, where models can recognize correct facts under constrained tests but fail to generate them in open‑ended settings. It demonstrates that SFT can cause both genuine wrong answers and expression‑level errors such as verbosity or formatting mismatches. To mitigate this, the authors propose Recall‑Anchored Distillation (RAD), a self‑distillation method that aligns the fine‑tuned model with the base model’s soft output distribution on unlabeled out‑of‑distribution text, thereby recovering lost factual recall without needing labeled data.
Joint-embedding predictive architectures (JEPAs) learn latent dynamics for planning and avoid representation collapse by matching features to maximum-entropy distributions such as isotropic Gaussians,...
Standard decoding rules for autoregressive language models promote diversity by rescaling the full next-token distribution or truncating its low-probability tail. These strategies overlook a common re...
Regulation (EU) 2024/886 obliges European payment service providers to settle euro credit transfers in under ten seconds, around the clock. This removes both the overnight batch window in which anti-m...
Researchers must often choose between Bayesian or neural network models of behavior, two paradigms with complementary strengths and weaknesses. An ideal paradigm would facilitate testing many kinds of...
arXiv:2608. 19662v1 Announce Type: new Abstract: Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard prefix caching from reusing their key--value (KV) states.
arXiv:2608. 19395v1 Announce Type: cross Abstract: Hybrid Transformer-Mamba large language models (LLMs) enhance long-context efficiency, but their heterogeneous computation and communication patterns complicate efficient hardware acceleration.
arXiv:2608. 20334v1 Announce Type: new Abstract: We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing.
arXiv:2608. 20208v1 Announce Type: new Abstract: Offline reinforcement learning improves robotic policies using previously collected data without further environment interaction.
arXiv:2608. 19536v1 Announce Type: cross Abstract: Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to variations in point density, scan pattern, viewpoint, and sensor characteristics.
arXiv:2608. 20172v1 Announce Type: new Abstract: Attention directly derives normalized information flow from pairwise scores.
arXiv:2605. 06094v5 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories.
arXiv:2608. 19938v1 Announce Type: cross Abstract: Existing approaches to anomalous behaviour log detection, such as Wazuh rely primarily on predefined detection rules, while statistical anomaly detection approaches such as OpenSearch identify deviations from previously observed behavioural patterns.
arXiv:2608. 19973v1 Announce Type: cross Abstract: Recently, open-vocabulary 3D object detection (3D-OVD) has gained increasing attention for its ability to detect unseen objects in 3D scenes.
arXiv:2602. 13710v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models enable instruction-following embodied control, but their large compute and memory footprints hinder deployment on resource-constrained robots and edge platforms.