Squeeze10-LLM is a staged mixed‑precision post‑training quantization framework that reduces 16‑bit LLM weights to an average of 1.6 bits per weight by assigning 80% of weights to 1 bit and 20% to 4 bits. It introduces Post‑Binarization Activation Robustness (PBAR), a weight significance metric that considers activation impact, and Full Information Activation Supervision (FIAS), a strategy that preserves activation information to limit error propagation. Experiments on LLaMA and LLaMA2 demonstrate that Squeeze10‑LLM achieves state‑of‑the‑art performance for sub‑2‑bit weight‑only quantization, raising average accuracy from 43% to 56% on six zero‑shot classification tasks.
By Qingcheng Zhu, Yangyang Ren, Linlin Yang, Yanjing Li, Sheng Xu, Haodong Zhu, Juan Zhang, Runqi Wang, Baochang Zhang
arXiv:2609.06076v1 Announce Type: new
Abstract: Retraining-free MoE compression reduces deployment memory by pruning or merging experts, but often treats the compressed checkpoint as the final artifa...
By Sieun Hyeon, Jaeyoung Do
arXiv:2609.07937v1 Announce Type: cross
Abstract: Structured visual reasoning, such as image puzzles, demands fine-grained visual perception, an ability current Vision Language Models (VLMs) lack. VL...
By Harsha Patnala, Debopriyo Banerjee, Ayush Sunil Munot, Somak Aditya
arXiv:2609.07566v1 Announce Type: new
Abstract: Caching systems often rely on simple eviction policies such as Least Recently Used (LRU) and Least Frequently Used (LFU), which perform well in complem...
By Younes Ben Mazziane, Xinying Zou
arXiv:2609.06542v1 Announce Type: cross
Abstract: The evolution of modern-day communication networks towards optical solutions with enhanced capacity and robustness is driving interest in topological...
By Benquan Wang, Trishita Das, Yuhan Peng, Tatjana Kleine, Shanshan Chang, Jinhui Chen, Nilo Mata-Cervera, Chunyu Li, Kelin Xia, Andrew Forbes, Yijie Shen
arXiv:2609.08709v1 Announce Type: new
Abstract: Designing foundation models for graphs is challenging due to the irregular structure of graphs and the different sizes and characteristics of embedding...
By Jonathan Frank, David Richerby, Ansgar Scherp
The paper introduces Open Tabular Insight Extraction (OpenTI), a unified framework aimed at democratizing access to insights from large table corpora. It highlights how current research is fragmented across domains like table QA, text‑to‑SQL, and data analysis agents, and shows that existing systems and benchmarks fall short of covering the full end‑to‑end scope of OpenTI. The authors propose a consolidated terminology, conduct a systematic review, and outline a research agenda for developing comprehensive OpenTI systems, evaluation methods, and interaction paradigms.
By Daniel Gomm, Maarten de Rijke, Madelon Hulsebos
arXiv:2609.06154v1 Announce Type: new
Abstract: One-shot federated graph learning generally aims to train Graph Neural Networks (GNNs) across clients with disconnected subgraphs in a single communica...
By Shutong Zheng, Sijia Chen
The paper introduces the Multi-Session Personalized Tool Calling (MPT) benchmark, containing 4,695 instances across 459 multi‑session histories that test Preference Recall, Induction, and Transfer. It proposes PRefine, a test‑time memory method that refines a user’s latent preference via a generate‑verify‑refine loop. Experiments with five LLMs show that PRefine outperforms existing memory systems and even full‑history prompting on Preference Transfer, suggesting that personalized agents should encode behavior as preferences rather than merely storing past interactions.
By Yejin Yoon, Minseo Kim, Taeuk Kim
The paper tackles selecting a cost‑constrained set of experiments that most effectively tighten bounds on a partially identifiable causal query. It formalizes this as the NP‑hard max‑potency problem, introduces efficient graphical pruning rules to reduce the search space, and demonstrates the approach on synthetic graphs and real NHANES data to estimate the effect of physical activity on diabetes.
By Tobias Maringgele, Jalal Etesami
The paper introduces Suan, a new preference optimization algorithm designed to improve safety alignment in large language models. Suan operates directly at the gradient level, avoiding traditional variational derivations, which yields more interpretable and robust training dynamics. Experiments show that Suan outperforms existing methods, achieving superior safety alignment while maintaining response utility.
By Oleksandr Cherednichenko, Roman Klypa
The paper introduces RouteCert, a method for ensuring risk control in multimodal systems that acquire inputs adaptively. It shows that conditional calibration can remain valid even when the acquisition policy determines the calibration group, and provides two finite‑sample constructions: threshold‑free routing with terminal‑pattern calibration and simultaneous validation of policy‑pattern pairs. Experiments on a clinical ECG task and masked multimodal benchmarks demonstrate that RouteCert achieves low disagreement rates and competitive answered fractions while validating each acquisition stage separately.
By Melika Baghi
HyCO is a hybrid neural solver that combines a sequential reinforcement learning (RL) solver with a global diffusion model (DM) to tackle combinatorial optimization problems. The RL component builds an initial solution prefix, after which HyCO switches to a conditional DM to finish the remaining decisions. The authors provide a theoretical framework showing that this hybrid approach yields lower expected regret than either method alone, identify an optimal trigger step for the switch, and implement a lightweight adaptive trigger based on policy entropy and RL‑DM disagreement, achieving consistent performance gains across benchmarks.
By Yuheng Li, Di Yang, Haipeng Chen, Yanhai Xiong
The fusion of hyperspectral (HS) and Light Detection and Ranging (LiDAR) data plays a crucial role in enhancing land-cover classification by jointly exploiting spectral, spatial, and structural cues....
Studies of the Model Context Protocol (MCP) server ecosystem draw their samples in ways that quietly select for servers that work: reference sets, popularity lists, hand-curated frames, or pipelines t...
A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently specified for faithful implementation. We study the codification readiness of im...
Enterprises deploy systems, not checkpoints. Usable capability depends jointly on weights, serving route, precision, output contract, and harness, yet all 18 audited benchmarks score advertised model...
Current LLM memory systems treat all personal facts identically, so stores grow without bound while retrieval precision degrades. The core challenge is lifecycle management: which memories should pers...
Sparse-view X-ray 3D reconstruction is essential for reducing radiation exposure, but recovering a density field from a handful of X-ray projections is severely ill-posed. Recently, 3D Gaussian Splatt...
Simultaneous assessment of medical imaging and patient records is often required in clinical diagnosis. However, standard machine learning algorithms cannot analyze these data types together. Meanwhil...