Global News Digest

Technology

arXiv

Argument Collapse: LLMs Flatten Long-Form Public Debate

LLMs flatten public debate by converging on a limited repertoire of arguments, producing significantly less unique content than humans. This "argument collapse" risks homogenizing long-form discourse.

arXiv

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models

THRD is a training-free framework defending LLMs against multi-turn jailbreaks by modeling temporal risk accumulation. It reduces attack success rates to 0.2–4.0% while preserving model utility.

arXiv

SECUREVENT: Hybrid AI/ML Security Monitoring for Distributed Event-Based Systems

SECUREVENT integrates AI/ML with traditional security to monitor distributed event-based systems. It outperforms static rules in detecting dynamic attacks while maintaining low false positives.

arXiv

Construction of Historical Knowledge Graphs Based on BERT and Graph Neural Networks

This study integrates BERT and GNNs to construct historical knowledge graphs, outperforming traditional methods in entity and relationship extraction. It also introduces a novel image retrieval system using FastRQNet and Vilt-qaformer+RoBInet.

arXiv

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

Adaptive Auto-Harness enables LLM agents to sustain self-improvement in dynamic, open-ended task streams. It outperforms baselines by adapting harnesses to shifting problem distributions via multi-agent evolution and routing.

arXiv

FLARE: Diffusion for Hybrid Language Model

FLARE converts hybrid LLMs to support both autoregressive and diffusion decoding via a unified checkpoint. This approach preserves model quality while boosting throughput for low-latency applications.

arXiv

Breaking the Information Silo: Semantic Personas for Cross-Domain Recommendation

SPHERE enables cross-domain recommendations for disjoint platforms by using LLMs to create semantic personas, bypassing the need for shared users or items.

arXiv

Multilinguality of Large Language Models From a Structural Perspective

This study analyzes LLM multilinguality structurally, finding low-resource languages diverge more from English. Post-training modifies these structures without disrupting inter-language relationships.

arXiv

MOSS-Audio Technical Report

MOSS-Audio is an audio-language model using DeepStack injection and time markers for precise temporal grounding. It supports captioning, transcription, and reasoning via 4B/8B variants, excelling in speech and general audio understanding.

arXiv

STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models

STaR-KV compresses GUI VLM KV caches via spatio-temporal re-weighting, cutting memory by 40% with negligible overhead. It outperforms existing methods in accuracy while maintaining high efficiency.

arXiv

ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference

ProbScale optimizes small language models by using probing to identify efficient subnetworks, reducing parameters 5-10x while retaining 95-98% of original accuracy.

arXiv

"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise

The authors introduce Decan, a novel diversity metric using in-context learning to score creative outputs without training. It effectively identifies diversity loss in AI models and correlates with human judgments.

arXiv

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

DySCo introduces dynamic, trust-aware sparse communication for LLM multi-agents, reducing overhead by selecting high-value links. It maintains consensus quality while lowering costs across reasoning tasks.

arXiv

Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation

This method accelerates protein dynamics emulation by applying a history-dependent bias to generative models, boosting diversity and coverage. It achieves up to 37x faster sampling and identifies more low-energy states than unbiased approaches.

arXiv

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

LayerRoute uses LoRA fine-tuning to enable agentic LLMs to skip transformer layers based on input type, reducing FLOPs by 15.25% for tool calls while maintaining high quality with minimal trainable parameters.

arXiv

Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses

This study reveals LLMs struggle significantly with non-verbal pragmatics, showing 60% lower accuracy than verbal tasks. While in-context learning helps, models still face major challenges in interpreting indirect non-verbal intent.

arXiv

Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection

The S³ framework suppresses forgery-specific shortcuts via subspace modeling, enhancing deepfake detection’s generalization. It uses training-time suppression and inference-time attenuation to improve cross-method performance without sacrificing in-domain accuracy.

arXiv

Boosting Multimodal Federated Learning via Chained Modality Optimization

FedMChain optimizes multimodal federated learning via sequential modality phases and sparse sign-guided aggregation, reducing modality competition and communication costs while boosting accuracy.

arXiv

RadioMaster: Multi-Agent System for Autonomous Radio Signal Generation

RadioMaster is a multi-agent system that autonomously converts user commands into physical wireless signals using domain knowledge and hardware-aware verification. It outperforms existing baselines in signal fidelity and configuration viability.

arXiv

Physics-Guided Attention in a Lightweight TCN for Efficient WiFi CSI-Based Human Activity Recognition

This study introduces a lightweight TCN for WiFi HAR using physics-guided attention. It outperforms deeper models while significantly reducing computational overhead.