SourceMay 28, 20262026-05-284 minVerified
Human-AI Collaboration in Scientific Replicability Assessment
Examines human-AI collaboration for replicability prediction, balancing speed and consistency against bias, accountability, and privacy risks.
SourceMay 28, 20262026-05-285 minVerified
MOV-Bench Reveals Gaps in Multi-Hop Video Reasoning
MOV-Bench highlights evaluation gaps in multi-hop audio-visual reasoning and shows consistent gains from agentic search.
SourceMay 28, 20262026-05-284 minVerified
Reassessing Offline RL for Code Generation Post-Training
Examines whether offline RL can cut online RL costs in code generation post-training without sacrificing practical quality.
SourceMay 28, 20262026-05-284 minVerified
Turning Papers Into Benchmarks With Agentic Reproduction Workflows
How under-specified applied ML papers can become executable benchmarks through agentic workflows and slot-based reporting.
SourceMay 23, 20262026-05-234 minVerified
Policy Layers for Governing Generalist LLM Agents Safely
How policy-as-code layers can govern generalist LLM agents by controlling tool use, approvals, and data exposure.
SourceMay 21, 20262026-05-215 minVerified
Multi-Model LLM Scheduling Under Offloading And Preemption Costs
Examines how offloading and preemption affect multi-model LLM serving under GPU memory limits and model-specific costs.
SourceMay 20, 20262026-05-204 minVerified
COBALT Rethinks Robot Learning Through Smartphone Teleoperation Data
COBALT proposes smartphone and cloud teleoperation to reduce data collection bottlenecks in robot imitation learning.
SourceMay 20, 20262026-05-204 minVerified
Limits of Handwritten Math Grading With Vision LLMs
In handwritten math grading, process understanding matters more than OCR, requiring rubric-based review and human checks.
SourceMay 20, 20262026-05-204 minVerified
Multi-Image Jailbreaks Expose Multimodal LLM Safety Gaps
Multi-image prompts can bypass single-image filters, exposing structural safety gaps in multimodal LLM defenses.
SourceApr 3, 20262026-04-033 minVerified
Wrapping Florence-2 for ROS 2 Robotic Integration
A case of wrapping Florence-2 with ROS 2 topics, services, and actions for local inference and reproducible integration.
SourceMar 31, 20262026-03-315 minVerified
Choosing Minimal GNN Extensions for Entity Resolution Tasks
A look at when entity resolution needs full GNN extensions and when task-specific minimal graph structure is enough.
SourceMar 31, 20262026-03-315 minVerified
Serverless Gossip Learning for Resilient Maritime AI Networks
How serverless gossip learning and carbon-aware orchestration address unreliable connectivity in maritime AI systems.
SourceMar 27, 20262026-03-275 minVerified
When AI Coding Quality Depends on Task Conditions
AI-generated code quality varies by task and prompt, so security, maintainability, and risk checks matter more than speed alone.
SourceMar 27, 20262026-03-275 minVerified
Distributed MADRL Scheduling for Large-Scale Cluster Systems
A look at distributed MADRL for large-scale scheduling, focusing on scalability, adaptability, and design tradeoffs.
SourceMar 27, 20262026-03-274 minVerified
Evaluating Harmful Manipulation in Multi-Turn AI Dialogue
A look at research evaluating harmful manipulation through human-AI multi-turn interaction beyond static benchmarks.
CommunityMar 27, 20262026-03-275 minVerified
How 1,250 AI Interviews Shape Product Decisions
Anthropic’s 1,250 AI-led interviews show how user research is shaping feature priorities and safety design.
SourceMar 27, 20262026-03-275 minVerified
NeuroVLM-Bench Tests Clinical Reasoning in Neuroimaging VLMs
A neuroimaging benchmark comparing vision-enabled LLMs on MRI and CT, focusing on clinical reasoning, errors, and safety tradeoffs.
SourceMar 27, 20262026-03-275 minVerified
Why Post-Training Collapses Multiple Valid Answers Into One
Examines how LLM post-training collapses multiple valid answers into one and why distributional evaluation matters.
SourceMar 27, 20262026-03-275 minVerified
RAG Security Risks From Combined Injection And Poisoning
Examines security risks in RAG when prompt injection and database poisoning combine across retrieval and indexing.
SourceMar 26, 20262026-03-264 minVerified
Execution Provenance Defines Real Agent Security Boundaries
Agent security depends less on benchmark scores than on tracing execution provenance across generation, handoffs, and permissions.
SourceMar 25, 20262026-03-254 minVerified
Minibal Reframes Game AI Around Balanced Human Play
Minibal asks whether game AI should optimize not for dominance, but for balanced, engaging play against humans.
SourceMar 20, 20262026-03-204 minVerified
How Segmentation Signals Drop And Recover In MLLMs
Analyzes how segmentation signals in MLLMs weaken in the adapter and recover through LLM attention across the pipeline.
SourceMar 20, 20262026-03-204 minVerified
Speaker Diarization Expands to Film and TV
Speaker diarization is moving from meetings to film and TV, where off-screen speech, noise, and subtitle drift matter.
SourceMar 18, 20262026-03-185 minVerified
Agent Governance Shifts From Rules To Execution Paths
Why agent governance is moving from static rules to execution paths, runtime logs, and timing-aware intervention.