Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding
arXiv:2601.17917v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel…
Explaining Group Recommendations via Counterfactuals
arXiv:2601.16882v2 Announce Type: cross Abstract: Group recommender systems help users make collective choices but often lack transparency, leaving group members…
When Agents Fail to Act: A Diagnostic Framework for Tool Invocation Reliability in Multi-Agent LLM Systems
arXiv:2601.16280v1 Announce Type: new Abstract: Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation…
Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging
arXiv:2601.16127v2 Announce Type: replace-cross Abstract: Fine-tuning a task-specific multilingual large language model (LLM) involves training the model on a multilingual…
LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
arXiv:2601.16890v1 Announce Type: cross Abstract: Automated fact-checking (AFC) systems are susceptible to adversarial attacks, enabling false claims to evade detection.…
A Mobile Application Front-End for Presenting Explainable AI Results in Diabetes Risk Estimation
arXiv:2601.15292v2 Announce Type: replace-cross Abstract: Diabetes is a significant and continuously rising health challenge in Indonesia. Although many artificial intelligence…
Gated Sparse Attention: Combining Computational Efficiency with Training Stability for Long-Context Language Models
arXiv:2601.15305v1 Announce Type: new Abstract: The computational burden of attention in long-context language models has motivated two largely independent lines…
Recommending Best Paper Awards for ML/AI Conferences via the Isotonic Mechanism
arXiv:2601.15249v2 Announce Type: replace-cross Abstract: Machine learning and artificial intelligence conferences such as NeurIPS and ICML now regularly receive tens…
FAIR-ESI: Feature Adaptive Importance Refinement for Electrophysiological Source Imaging
arXiv:2601.15731v1 Announce Type: cross Abstract: An essential technique for diagnosing brain disorders is electrophysiological source imaging (ESI). While model-based optimization…