arXiv:2608.18404v1 Announce Type: cross Abstract: We answer this question with Vector-Symbolic Policy Gradient (VSPG), a discrete-action actor that…
Author: script
Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B
arXiv:2608.18419v1 Announce Type: cross Abstract: Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling…
Formal Verification of Romanov’s Triplet Logic: A Verified Filter for Sliding-window 3-CNF with Application to Structured Formulas
arXiv:2608.18445v1 Announce Type: cross Abstract: We present the first mechanised formalisation of Romanov’s Triplet Logic (TLS) in the Rocq proof…
Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage
arXiv:2608.18438v1 Announce Type: cross Abstract: Modern mental healthcare faces a critical shortage of senior supervisory oversight, leading to a…
AI News Brief Hourly Summary 2026-08-20 17h : 15 posts
15 posts published in the last hour 14:33TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs 14:33Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation 14:33Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP…
TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs
arXiv:2608.18386v1 Announce Type: cross Abstract: Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like…
Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation
arXiv:2608.18379v1 Announce Type: cross Abstract: When every candidate is wrong, correct-candidate selection is unavailable, yet the aggregation call can…
Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents
arXiv:2608.18351v1 Announce Type: cross Abstract: Tool-using large language-model agents can complete a task while exercising authority that the user did…
Frontier Radar #4: China has caught up, so what’s left of the Western AI lead?
Kimi K3 and GLM-5.3 are now within striking distance of the best US models. Western labs blame distillation, and there’s real evidence for it. But guilty…
One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI
arXiv:2608.18360v1 Announce Type: cross Abstract: Agentic AI systems take consequential actions governed by more than one pre-action control at once:…