arXiv:2605.00371v1 Announce Type: cross Abstract: In this paper, we propose GaMMA, a state-of-the-art (SoTA) large multimodal model (LMM) designed to achieve comprehensive musical content understanding. GaMMA inherits the streamlined encoder-decoder design of LLaVA, enabling effective cross-modal learning between music and language. By incorporating audio encoders in a mixture-of-experts manner, GaMMA effectively unifies both time-series and […]
SIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding
arXiv:2605.00401v1 Announce Type: cross Abstract: Recent EEG-to-image retrieval methods leverage pretrained vision encoders and foveation-inspired priors, but typically assume a fixed, center-focused view. This center bias conflicts with content-driven human attention, creating a geometric-semantic dissociation between visual features and EEG responses. We propose SIMON, a saliency-aware multi-view framework for zero-shot EEG-to-image retrieval. SIMON combines foreground […]
Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines
arXiv:2605.00410v1 Announce Type: cross Abstract: A multi-agent pipeline with N agents typically issues N LLM calls per run. Merging agents into fewer calls (compound execution) promises token savings, but naively merged calls silently degrade quality through tool loss and prompt compression. We present Agent Capsules, an adaptive execution runtime that treats multi-agent pipeline execution as […]
RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI
arXiv:2605.00421v1 Announce Type: cross Abstract: Large language models (LLMs) show promise in radiology but their deployment is limited by computational requirements that preclude use in resource-constrained clinical environments. We investigate whether small language models (SLMs) of 3-4 billion parameters can achieve strong multi-task radiology performance through LoRA fine-tuning, enabling deployment on consumer-grade CPUs. We train […]
Rethinking Network Topologies for Cost-Effective Mixture-of-Experts LLM Serving
arXiv:2605.00254v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) architectures have turned LLM serving into a cluster-scale workload in which communication consumes a considerable portion of LLM serving runtime. This has prompted industry to invest heavily in expensive high-bandwidth scale-up networks. We question whether such costly infrastructure is strictly necessary. We present the first systematic cross-layer analysis […]
Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes
arXiv:2605.00424v1 Announce Type: cross Abstract: Agent skills — structured packages of instructions, scripts, and references that augment a large language model (LLM) without modifying the model itself — have moved from convenience to first-class deployment artifact. The runtime that loads them inherits the same problem package managers and operating systems have always faced: a piece […]
AlphaInventory: Evolving White-Box Inventory Policies via Large Language Models with Deployment Guarantees
arXiv:2605.00369v1 Announce Type: cross Abstract: We study how large language models can be used to evolve inventory policies in online, non-stationary environments. Our work is motivated by recent advances in LLM-based evolutionary search, such as AlphaEvolve, which demonstrates strong performance for static and highly structured problems such as mathematical discovery, but is not directly suited […]
Escaping Mode Collapse in LLM Generation via Geometric Regulation
arXiv:2605.00435v1 Announce Type: cross Abstract: Mode collapse is a persistent challenge in generative modeling and appears in autoregressive text generation as behaviors ranging from explicit looping to gradual loss of diversity and premature trajectory convergence. We take a dynamical-systems view and reinterpret mode collapse as reduced state-space accessibility caused by *geometric collapse*: during generation, the […]
BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs
arXiv:2605.00422v1 Announce Type: cross Abstract: Large language models (LLMs) have driven major progress in NLP, yet their substantial memory and compute demands still hinder practical deployment. Binarization can compress weights to 1 bit, fundamentally lowering compute and bandwidth cost. However, existing methods cannot address activation heavy tails and thus must keep activations in high precision, […]
Adaptation of AI-accelerated CFD Simulations to the IPU platform
arXiv:2605.00462v1 Announce Type: cross Abstract: Intelligence Processing Units (IPU) have proven useful for many AI applications. In this paper, we evaluate them within the emerging field of emphAI for simulation, where traditional numerical simulations are supported by artificial intelligence approaches. We focus specifically on a program for training machine learning models supporting a emphcomputational fluid […]
DynamicPO: Dynamic Preference Optimization for Recommendation
arXiv:2605.00327v1 Announce Type: cross Abstract: In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-feedback negatives and sharpen preference boundaries. However, our empirical analyses reveal a counterintuitive phenomenon, preference optimization collapse, where increasing the number of negative samples can lead […]
Scalable Context-Aware Graph Attention for Unsupervised Anomaly Detection in Large-Scale Mobile Networks
arXiv:2605.00482v1 Announce Type: cross Abstract: Mobile network operators must monitor thousands of heterogeneous network elements across the radio access network and the packet core, each exposing high-dimensional KPI time series. The scale and cost of incident labelling make supervised approaches impractical, motivating unsupervised anomaly detection robust to context shifts and nonstationarity. We propose textbfC-MTAD-GAT (emphContext-aware […]