arXiv AI
Jun 4
Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?
arXiv:2506. 10912v4 Announce Type: replace Abstract: Toxicity remains a leading cause of early-stage drug development failure.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv Machine Learning
Jun 4
RAVQ-HoloNet: Rate-Adaptive Vector-Quantized Hologram Compression
arXiv:2511. 21035v2 Announce Type: replace Abstract: Holography offers significant potential for AR/VR applications.
arXiv AI
Jun 4
Stochastic Sparse Attention for Memory-Bound Inference
arXiv:2605. 01910v2 Announce Type: replace-cross Abstract: Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all $n_k$ key and value vectors from KV cache.
arXiv AI
Jun 4
Geometry-Aware Distillation for Prompt Tuning Biomedical Vision-Language Models
arXiv:2606. 04922v1 Announce Type: cross Abstract: Current prompt-based and adapter-based tuning of vision-language models (VLMs) is attractive for medical imaging, where clinical data sensitivity favors frozen backbones and annotations are limited.
arXiv Machine Learning
Jun 4
Latent Anchor-Driven Test Generation for Deep Neural Networks
arXiv:2606. 04310v1 Announce Type: new Abstract: Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses.
arXiv Machine Learning
Jun 4
Episodic Memory Temporal Consistency for Cooperative Multi-Agent Reinforcement Learning
arXiv:2606. 04492v1 Announce Type: new Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) frequently suffers from severe reward sparsity and exploration bottlenecks.
arXiv Machine Learning
Jun 4
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
arXiv:2606. 04980v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in memory.
arXiv Machine Learning
Jun 4
Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks
arXiv:2606. 04317v1 Announce Type: cross Abstract: Deep neural networks are increasingly deployed across heterogeneous and partially untrusted environments, where models are distributed through cloud storage, CI/CD pipelines, containerized services, and edge execution platforms.
arXiv AI
Jun 4
ANN Search: Recall What Matters
arXiv:2606. 04522v1 Announce Type: cross Abstract: Approximate nearest neighbor (ANN) search has become a core primitive in information retrieval and modern machine learning tasks, from classification to retrieval-augmented generation.
arXiv Machine Learning
Jun 4
Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning
arXiv:2606. 04434v1 Announce Type: cross Abstract: Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleaved image-text In-Context Demonstrations (ICDs) conditions the model to solve new tasks.
arXiv AI
Jun 4
L-TGVN: Leveraging Longitudinal Priors for Personalized Rapid MRI
arXiv:2606. 04419v1 Announce Type: cross Abstract: MRI provides excellent soft-tissue contrast without ionizing radiation, but long acquisition times increase patient discomfort while also raising exam costs and limiting scanner throughput.
arXiv Machine Learning
Jun 4
SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
arXiv:2606. 04511v1 Announce Type: cross Abstract: Sparse attention reduces compute and memory bandwidth for long-context LLM inference.
arXiv AI
Jun 4
DSIRM: Learning Query-Bridged Discrete Semantic Identifiers for E-commerce Relevance Modeling
arXiv:2606. 04374v1 Announce Type: cross Abstract: Despite rapid progress of continuous embeddings for e-commerce search relevance, a long-standing open problem is the difficulty in capturing fine-grained attribute distinctions.
arXiv Machine Learning
Jun 4
BBOmix: A Tabular Benchmark for Hyperparameter Optimization of Unsupervised Biological Representation Learning
arXiv:2606. 05139v1 Announce Type: new Abstract: The rapid advancement of high-throughput sequencing has led to large, high-dimensional omics datasets.
arXiv AI
Jun 4
Model-Preserving Adaptive Rounding
arXiv:2505. 22988v3 Announce Type: replace-cross Abstract: The goal of quantization is to produce a compressed model whose output distribution is as close to the original model's as possible.
arXiv AI
Jun 4
LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation
arXiv:2605. 29280v2 Announce Type: replace-cross Abstract: Knowledge distillation (KD) transfers a single scalar prediction from a large foundation model (FM) to compact vertical models (VMs), suffering from diminishing transfer ratio -- the fraction of FM improvement captured by the VM -- as a single scalar cannot convey the rich intermediate knowledge that larger FMs learn.
arXiv AI
Jun 4
Channel-Oriented Design for EEG-to-Music Reconstruction
arXiv:2606. 04040v1 Announce Type: cross Abstract: Brain-computer interfaces aim to decode naturalistic stimuli from neural signals, yet most progress to date has focused on vision and language.
arXiv AI
Jun 4
MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models
arXiv:2606. 04349v1 Announce Type: cross Abstract: Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language Models (OLLMs) due to the extreme distribution heterogeneity and disparate outlier patterns across modalities.
arXiv AI
Jun 4
Constrained Adaptive Rejection Sampling
arXiv:2510. 01902v2 Announce Type: replace Abstract: Language Models (LMs) are increasingly used in applications where generated outputs must satisfy strict semantic or syntactic constraints.
arXiv Machine Learning
Jun 4
SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models
arXiv:2602. 01027v2 Announce Type: replace Abstract: Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets.