đ HISTORICAL ARCHIVE - June 21, 2026
What was happening in AI on 2026-06-21
đ You are visitor #47291 to this AWESOME site! đ
Archive from: 2026-06-21 | Preserved for posterity âĄ
đ Filter by Category
Loading filters...
đ° NEWS
đē 4 pts
⥠Score: 8.3
đŦ RESEARCH
via Arxiv
đ¤ Abdul Rafay Syed
đ
2026-06-18
⥠Score: 8.1
"Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure. We investigate whether this misalignment corresponds to a causally actionable activation-space direction shared across architectures. Across four instruction-tuned model families (Qw..."
đŦ RESEARCH
via Arxiv
đ¤ Arastoo Zibaeirad, Marco Vieira
đ
2026-06-18
⥠Score: 7.4
"Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved. We present CWE-Trace, a framework for LLM vulnerability detection built from 834 manually curated Linux kernel samples spanning 74 CWEs. The framewor..."
đ° NEWS
đē 1 pts
⥠Score: 7.3
đŦ RESEARCH
"Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches. This is highly effective for high-throughput, high-concurrency serving, but it manages only one positional fragment of execution state: the KV cache. We study the opposite regime: low-latency, small..."
đ° NEWS
đē 173 pts
⥠Score: 7.0
đ° NEWS
đē 4 pts
⥠Score: 7.0
đŦ RESEARCH
via Arxiv
đ¤ Joshua Engels, Callum McDougall, Bilal Chughtai et al.
đ
2026-06-18
⥠Score: 7.0
"LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. However, DiffusionGemma performs a larger fraction of its computation in a continuous latent space; does this make its reasoning less t..."
đŦ RESEARCH
via Arxiv
đ¤ Shu Yao, Yuhua Luo, Qian Long et al.
đ
2026-06-18
⥠Score: 6.9
"Real-world computer-use tasks often span multiple applications and devices, requiring agents to coordinate heterogeneous environments under dynamic runtime failures. Existing multi-device agent systems support task decomposition and cross-device assignment, but recovery remains largely coarse-graine..."
đŦ RESEARCH
via Arxiv
đ¤ Sihui Dai, Mann Patel
đ
2026-06-18
⥠Score: 6.9
"Prior work has shown that in-context demonstrations can jailbreak language models, but it remains unclear how models interpret different types of compliance demonstrations. We study this by mixing benign compliance demonstrations (non-harmful request, helpful response) with harmful compliance demons..."
đ ī¸ SHOW HN
đē 2 pts
⥠Score: 6.8
đĄ AI NEWS BUT ACTUALLY GOOD
The revolution will not be televised, but Claude will email you once we hit the singularity.
Get the stories that matter in Today's AI Briefing.
Powered by Premium Technology Intelligence Algorithms âĸ Unsubscribe anytime
đ° NEWS
đē 1 pts
⥠Score: 6.8
đŦ RESEARCH
via Arxiv
đ¤ Jun He, Deying Yu
đ
2026-06-18
⥠Score: 6.8
"Autonomous agents are increasingly connected to cloud, deployment, and data-control workflows, but production mutation authority should not reside inside non-deterministic reasoning processes. Existing access-control mechanisms authorize identities, while assurance layers certify proposed actions; n..."
đŦ RESEARCH
via Arxiv
đ¤ Alaia Solko-Breslin, Pramod Kaushik Mudrakarta, Mihai Christodorescu et al.
đ
2026-06-18
⥠Score: 6.7
"Securing AI agents that operate in complex digital environments has become a critical need, and runtime monitoring approaches that formulate and enforce policies expressed in a formal language like Datalog offer a promising solution. However, existing approaches are restricted to deterministic polic..."
đŦ RESEARCH
"When large language models serve as evaluators in multi-agent systems, their systematic evaluation biases propagate through the agent network. We introduce Contagion Networks, a formal framework for measuring how evaluator biases spread across interacting LLM agents. In a controlled 3-agent experime..."
đŦ RESEARCH
via Arxiv
đ¤ Md Nayem Uddin, Amir Saeidi, Eduardo Blanco et al.
đ
2026-06-18
⥠Score: 6.6
"Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relevant facts, identifiers, constraints, and conditions observed through user interaction and tool calls. In standard agents..."
đŦ RESEARCH
via Arxiv
đ¤ Shiguo Lian, Kai Wang, Zhaoxiang Liu et al.
đ
2026-06-18
⥠Score: 6.5
"Large model inference optimization serves as a key foundation for supporting the scalable, low-cost, and highly stable operation of large model services. Centered on token-oriented inference optimization technology, this paper proposes for the first time a four-layer technical architecture consistin..."
đ ī¸ SHOW HN
đē 1 pts
⥠Score: 6.2
đŦ RESEARCH
via Arxiv
đ¤ Harshit Singh, Ayush Pratap Singh, Nityanand Mathur
đ
2026-06-18
⥠Score: 6.1
"Flow-matching text-to-speech systems achieve remarkable zero-shot quality but remain static after deployment: pronunciation errors on out-of-vocabulary proper nouns persist unless the model is retrained. We introduce FlowEdit, a life-long adaptation framework for frozen flow-matching TTS that learns..."
đ ī¸ SHOW HN
đē 2 pts
⥠Score: 6.1
đ ī¸ SHOW HN
đē 2 pts
⥠Score: 6.1