Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2605. 09253v2 Announce Type: replace-cross Abstract: While recent work in Reinforcement Learning with Verifiable Rewards (RLVR) has shown that a small subset of critical tokens disproportionately drives reasoning gains, an analogous token-level understanding of On-Policy Distillation (OPD) remains largely unexplored.
arXiv:2606. 02355v1 Announce Type: new Abstract: Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency.
arXiv:2606. 01352v1 Announce Type: new Abstract: Watch time has emerged as a pivotal metric for optimizing deep user engagement in short-video recommender systems.
arXiv:2606. 00928v1 Announce Type: cross Abstract: Multiplexed fluorescence microscopy improves tissue segmentation by providing complementary channels including nuclear (DAPI) and membrane (E-cadherin), that together encode richer spatial context than single-channel imaging alone.
arXiv:2604. 26283v3 Announce Type: replace-cross Abstract: High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during image interpretation.
arXiv:2602. 08585v2 Announce Type: replace-cross Abstract: Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference.
arXiv:2606. 00889v1 Announce Type: cross Abstract: Phishing attacks remain a major cybersecurity threat, exploiting deceptive URLs to steal sensitive user information.
arXiv:2606. 01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives.
arXiv:2605. 07804v3 Announce Type: replace-cross Abstract: On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models.
arXiv:2606. 00422v1 Announce Type: cross Abstract: Modern recommendation systems predominantly train retrieval and ranking as separate models despite both increasingly relying on large transformers encoding the same user behavior data, duplicating parameters, compute, and serving cost.
arXiv:2606. 00404v1 Announce Type: cross Abstract: Implicit neural representations (INRs) model a signal as a continuous coordinate-to-value function.
arXiv:2606. 01923v1 Announce Type: cross Abstract: Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations.
arXiv:2601. 22900v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning across domains, but outcome-only scalar rewards are often sparse and uninformative.
arXiv:2303. 04345v2 Announce Type: replace Abstract: Federated learning (FL) is a promising framework that models distributed machine learning while protecting the privacy of clients.
arXiv:2606. 01537v1 Announce Type: cross Abstract: Clinical diagnosis often requires combining imaging with physiological measurements, yet deployed models typically operate on unimodal data.
arXiv:2602. 10056v2 Announce Type: replace Abstract: We introduce WildCat, a high-accuracy, low-cost approach to compressing the attention mechanism in neural networks.
arXiv:2606. 00079v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory.
arXiv:2606. 00390v1 Announce Type: cross Abstract: We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with a small number of shared transformer blocks.
arXiv:2606. 00129v1 Announce Type: cross Abstract: Large language models (LLMs) have emerged as powerful representation learners whose internal features increasingly align with human cognition.
arXiv:2606. 00120v1 Announce Type: cross Abstract: This paper proposes SpikeWFM, a novel hybrid architecture that integrates spiking neural networks (SNNs) with conventional artificial neural network (ANN)-based transformers for wireless foundation models (WFMs).