SourceJun 24, 20262026-06-245 minVerified
CineCap And The Challenge Of Cinematic Video Captioning
CineCap targets cinematic video captioning, focusing on camera motion, shot size, angle, and structured scene reasoning.
SourceJun 24, 20262026-06-244 minVerified
HOLMES Challenges LLMs With Higher-Order Logic Reasoning
HOLMES probes higher-order logic reasoning beyond final answers, exposing limits in LLM rule, predicate, and constraint handling.
SourceJun 23, 20262026-06-234 minVerified
The AI Evaluability Gap in Risk Governance
Why AI deployment decisions depend not just on performance, but on sufficient evaluation evidence and governance links.
SourceJun 23, 20262026-06-233 minVerified
RLHF Alignment Through the Lens of Social Choice
A look at recent research framing RLHF as preference aggregation, with implications for fairness and safety.
SourceJun 23, 20262026-06-234 minVerified
Role-Based Agentic AI for Intent-Driven Network Operations
Examines role-based agentic AI for intent-driven telecom operations, with focus on autonomy, orchestration, and safety.
CommunityJun 23, 20262026-06-234 minVerified
UK Backs Open AI on Everyday Hardware
The UK funds open AI and general-purpose hardware research to expand access, efficiency, and tech autonomy.
CommunityJun 22, 20262026-06-224 minVerified
AI, Fermi Paradox, and the Meaning of L
A look at the Fermi Paradox through Drake equation variable L, observation limits, and AI risk claims.
CommunityJun 20, 20262026-06-204 minVerified
AI Coding Needs Review More Than Speed Gains
AI coding can boost output, but not quality or accountability. The real bottleneck is review, validation, and approval.
SourceJun 20, 20262026-06-204 minVerified
How Linear Transformer FFN Blocks Really Are
Examines per-block linear recoverability of transformer FFNs and what R^2_lin may imply for compression and interpretability.
SourceJun 20, 20262026-06-203 minVerified
How LLMs Encode Essay Quality for Scoring
Examines how LLMs encode essay quality in hidden representations and whether those signals persist across prompt changes.
SourceJun 20, 20262026-06-203 minVerified
Interpreting Style-Caption TTS With Cross-Attention Attribution
A look at why cross-attention attribution matters for interpreting word-level style control in caption-based TTS.
SourceJun 20, 20262026-06-204 minVerified
JustDiag for Auditable Root Cause Analysis in LLM Workflows
Why JustDiag reframes LLM root cause analysis around evidence, alternatives, contradictions, and uncertainty.
SourceJun 20, 20262026-06-204 minVerified
Measuring False Intervention in DeFi Supervisory AI Agents
Why DeFi supervisory AI should measure false intervention separately from accuracy, with practical checks for evaluation.
SourceJun 20, 20262026-06-204 minVerified
Query Placement Matters in Diffusion LLM In-Context Learning
Why query placement may affect diffusion LLM in-context learning, and what prior position-bias results imply.
SourceJun 20, 20262026-06-204 minVerified
When Learner-Based Drift Detection Works Better in Streaming
Explains when learner-based drift detection outperforms statistical tests in streaming ML and what matters operationally.
SourceJun 19, 20262026-06-194 minVerified
Can General Models Extract Legal Networks Reliably
Using FineREX, this examines why legal-record extraction for smuggling knowledge graphs needs domain-specific schemas and review.
SourceJun 19, 20262026-06-193 minVerified
Self-Review Alignment for Safer LLM Reasoning Outputs
Explores combining a conscience step with DPO so LLMs review reasoning during inference while balancing safety and performance.
SourceJun 12, 20262026-06-124 minVerified
Reframing Shielded RL as Design-Time Structure Analysis
A concise look at shielded RL reinterpreted as a design-time tool for structural safety analysis, not runtime blocking.
CommunityJun 12, 20262026-06-123 minVerified
Rethinking AI Job Impacts Beyond Mass Unemployment Fears
Official reports suggest AI is reshaping tasks and productivity before causing broad job losses.
SourceJun 12, 20262026-06-123 minVerified
Rethinking AI Loss of Control Through Operational Definitions
Examines vague AI loss-of-control language and reframes it around goals, audits, interruption, and rollback.
SourceJun 2, 20262026-06-024 minVerified
Why Mechanistic Interpretability Needs Auditable Validation Rules
Mechanistic interpretability matters, but auditable, reproducible validation rules are what safety-critical AI needs.
SourceJun 2, 20262026-06-024 minVerified
TriLens Tracks Hallucination Signals Across LLM Internal Layers
TriLens explores white-box hallucination detection by tracking layer-wise entropy signals before incorrect answers emerge.
SourceJun 1, 20262026-06-015 minVerified
Do Warm Personalized AI Replies Persuade Users More?
Examines how contextual personalization and warmth affect trust, persuasion, and reliance in conversational AI.
CommunityJun 1, 20262026-06-014 minVerified
Why AI Stops Reproducing Lyrics and Long Texts
Why AI services often block long copyrighted text reproduction but allow transforms of user-provided text.