Spark-Audio 1.0 Technical Report
Spark-Audio 1.0, trained on domestic hardware, matches Qwen3.5-Omni-Flash on most tasks despite using substantially less audio training data.
AI Research Radar
Friday, October 23: 3 frontier papers out of 409 read.
Frontier
Papers rated as moving the field
How we chooseEpiSEM-Bench
The benchmark reveals substantial variation across ten models in omission robustness, evidence acquisition, and appropriate action.
IQuest-Q1
This week in research
Oct 17–23: 318 cleared, 29 frontier
- Security114◆ 1
- Safety60◆ 13
- Agents37◆ 6
- Robotics25◆ 4
- Society20
- 4 moreScience, Training, Reasoning, ML20◆ 2
- Language16◆ 2
- Vision13◆ 1
- Inference13
- Security114◆ 1
- 8 moreSociety, Language, Vision, Inference, Science, Training, Reasoning, ML82◆ 5
- Safety60◆ 13
- Agents37◆ 6
- Robotics25◆ 4
Size: cleared papers◆ and tint: frontier papers
Models under test
Papers this week that name the model
Labs publishing
Papers this week with an author at the lab
Also cleared
45 papers, by field
Security & privacy17
- MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
- PhishGen: Understanding LLM Capabilities in Automated Phishing Website Generation
- Automated screening of privacy risks in medical AI
- Mirage: Targeted Jailbreaks Against Post-Generation Safety Checkers in Multimodal Diffusion Models
- The Psychology of an AI Hacker
All 17 papers in Security & privacy
- Data-Void Exploits in Web-Searching LLMs
- Not Where You Think: Protecting Location Privacy Against Reasoning-Based Geolocation
- Membership Inference Attack on Private Evolution
- HiMark: Hierarchical and Controllable Multi-bit Watermarking for Large Language Models
- Your Token Is Gone: A Token-Consumption Countermeasure for Disrupting LLM-Based Scam Systems
- Amplifying Latency and Cost of LLM Inference via Rowhammer Attack
- MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition
- ReDence: A Hybrid Agentic and Decision-Model Framework for Rapid, Evidence-Grounded Detection of Modern Social Engineering Scams
- Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models
- AgentPhishing: A Benchmark of LLM Email Agents Under Adaptive Attack
- Diffusion Language Models for Perplexity-Aware Black-Box Attacks
- Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure
AI & society8
- The Delegation Divide: An Open Index of AI-Agent Delegability across Occupations and CountriesCode
- The Customer Is the Builder: How AI Coding Agents Are Rewriting the Economics of Software
- From Tokens to Credits to Outcomes: Pricing AI Across Models, Applications, and Cloud Platforms
- Joules-to-GDP: How Much Economic Value Do AI Systems Produce per Unit of Energy?
- Truthful by Omission: Click Thinning for LLM-Native Advertising
Safety & alignment7
- Detecting AI Training in Datacentre Power
- Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
- A Three-Pillar Governance Framework for Safe and Trustworthy AI Agents
- From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots
- UniGuard: Multi-View Guardrail Learning for Cross-Interface Safety Generalization
Agents6
- MCP vs CLI for AI Agents: A Comparative Analysis of Tool Integration Strategies for Autonomous SystemsMicrosoft
- PLE: Physical-Engineering's Last ExamGoogle
- Governance-State Corruption in Long-Term Memory for LLM Agents: A Cross-Model Stress Test
- LLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades
- AgentVQA: A Unified Benchmark for Agentic Visual Understanding
- BrickWright: Agentic Creation of Physically Feasible Brick Builds