- Symphonym: Universal Phonetic Embeddings for Cross-Script Name Matching
Stephen Gadd · Jan 11, 2026
Linking names across historical sources, languages, and writing systems remains a fundamental challenge in digital humanities and geographic information retrieval.
- Mixture-of-Experts as Soft Clustering: A Dual Jacobian-PCA Spectral Geometry Perspective
Feilong Liu · Jan 9, 2026
Mixture-of-Experts (MoE) architectures are widely used for efficiency and conditional computation, but their effect on the geometry of learned functions and representations remains poorly understood.
- HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue
Laya Iyer, Kriti Aggarwal, Sanmi Koyejo, Gail Heyman, Desmond C. Ong · Jan 9, 2026
Pairwise PreferenceRubric Rating
Despite rapid progress in language models, we still lack a clear way to understand how their abilities in these interpersonal domains compare to those of humans.
- Neurosymbolic Retrievers for Retrieval-augmented Generation
Yash Saxena, Manas Gaur · Jan 8, 2026
Retrieval Augmented Generation (RAG) has made significant strides in overcoming key limitations of large language models, such as hallucination, lack of contextual grounding, and issues with transparency.
- What Matters For Safety Alignment?
Xing Li, Hui-Ling Zhen, Lihao Yin, Xianzhi Yu, Zhenhua Dong · Jan 7, 2026
Red Team Tool Use
This paper presents a comprehensive empirical study on the safety alignment capabilities.
- Stratified Hazard Sampling: Minimal-Variance Event Scheduling for CTMC/DTMC Discrete Diffusion and Flow Models
Seunghwan Jang, SooJean Han · Jan 6, 2026
Uniform-noise discrete diffusion and flow models (e.g., D3PM, SEDD, UDLM, DFM) generate sequences non-autoregressively by iteratively refining randomly initialized vocabulary tokens through multiple context-dependent replacements.
- SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation
Hanqi Jiang, Junhao Chen, Yi Pan, Ling Chen, Weihang You · Jan 6, 2026
While Large Language Models (LLMs) excel at generalized reasoning, standard retrieval-augmented approaches fail to address the disconnected nature of long-term agentic memory.
- Embedding Retrofitting: Data Engineering for better RAG
Anantha Sharma · Jan 6, 2026
Embedding retrofitting adjusts pre-trained word vectors using knowledge graph constraints to improve domain-specific retrieval.
- The Invisible Hand of AI Libraries Shaping Open Source Projects and Communities
Matteo Esposito, Andrea Janes, Valentina Lenarduzzi, Davide Taibi · Jan 5, 2026
In the early 1980s, Open Source Software emerged as a revolutionary concept amidst the dominance of proprietary software.
- CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
Shuhang Chen, Yunqiu Xu, Junjie Xie, Aojun Lu, Tao Feng · Jan 5, 2026
Motivated by this, we present CogFlow, a novel cognitive-inspired three-stage framework that incorporates a knowledge internalization stage, explicitly simulating the hierarchical flow of human reasoning: perception$\Rightarrow$internalizat
- ARGUS: Adaptive Rotation-Invariant Geometric Unsupervised System
Anantha Sharma · Jan 3, 2026
Pairwise Preference
Detecting distributional drift in high-dimensional data streams presents fundamental challenges: global comparison methods scale poorly, projection-based approaches lose geometric structure, and re-clustering methods suffer from identity in
- Improving Variational Autoencoder using Random Fourier Transformation: An Aviation Safety Anomaly Detection Case-Study
Ata Akbari Asanjan, Milad Memarzadeh, Bryan Matthews, Nikunj Oza · Jan 3, 2026
We showcase our findings with two low-dimensional synthetic datasets for data representation, and an aviation safety dataset, called Dashlink, for high-dimensional reconstruction-based anomaly detection.
- Fast-weight Product Key Memory
Tianyu Zhao, Llion Jones · Jan 2, 2026
Notably, in Needle-in-a-Haystack evaluations, FwPKM generalizes to 128K-token contexts despite being trained on only 4K-token sequences.
- RAIR: A Rule-Aware Benchmark Uniting Challenging Long-Tail and Visual Salience Subset for E-commerce Relevance Assessment
Chenji Lu, Zhuo Chen, Hui Zhao, Zhenyi Wang, Pengjie Wang · Dec 31, 2025
While large language models (LLMs) have shown significant results on relevance task, existing benchmarks lack sufficient complexity for comprehensive model assessment, resulting in an absence of standardized relevance evaluation metrics acr
- WISE: Web Information Satire and Fakeness Evaluation
Gaurab Chhetri, Subasish Das, Tausif Islam Chowdhury · Dec 30, 2025
This study develops WISE (Web Information Satire and Fakeness Evaluation) framework which benchmarks eight lightweight transformer models alongside two baseline models on a balanced dataset of 20,000 samples from Fakeddit, annotated as eith
- Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
Ang Lv, Jin Ma, Yiyuan Ma, Siyuan Qiao · Dec 29, 2025
Mixture-of-Experts (MoE) models lack explicit constraints to ensure the router's decisions align well with the experts' capabilities, which ultimately limits model performance.
