June 13–19: 18 frontier papers out of 2,065 read.
Papers rated as moving the field
How we choose“Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents.”
The authors, in the abstract
Omnimodal World Models for Physical AI
“In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2.”
“Nemotron 3 Ultra achieves up to 6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy.”
“We show that reinforcement learning can make a policy \emph{addicted} to such a visible self-benefit channel.”
“Evaluating 15 advanced agents reveals that robust spatial task solving remains challenging: the strongest model, GPT-5, achieves an average task success rate (TSR) of only 17.4%, while the leading open-source model, Qwen-3.5, reaches 14.1%.”
“GPT-5.5 with Codex performs best, solving 16.1% of web exploitation tasks and 31.7% of post-exploitation tasks; with more concrete hints, these rates increase to 33.0% and 46.3%.”
“Cross-architecture transfer via ridge regression maps yields large behavioral suppression (up to 46 points) but fails specificity controls as random and orthogonal directions perform comparably.”
“On multi-UAV mobile-edge computing, autonomous intersection management, and a hybrid SMAC variant, TRIDENT cuts training-time violations by 95.5% over MADDPG and 76.3% over MACPO, while improving reward by 13.5% over the strongest unconstrained baseline.”
“We demonstrate that the attack amplifies privacy leakage across language (up to 100% successful extraction), and vision-language models (up 90% successful extraction).”
“The strongest adaptive search (tree-of-attacks) breaks Opus 4.8 on 11.5% of intents overall, whereas Fable 5 stays in the single digits (6.1% worst-case).”
“Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core.”
“Experiments show that GeoDisaster challenges existing RS-VLMs and agentic systems, while RCEA improves tool use, evidence grounding, state consistency, and decision generation.”
“Our experiments using a custom decomposer show that state-of-the-art agents exhibit high refusal rates on monolithic harmful tasks, but significantly lower refusal rates on their decomposed variants, while often inadvertently fulfilling the adversarial objectives.”
“Our results show that reward hacking arises naturally when optimizing proxy objectives with capable language model agents and resists standard mitigations, suggesting that proxy-reward failures in agentic settings may require approaches beyond standard exploration and credit-assignment fixes.”
“Extensive experiments demonstrate that our method achieves surgical concept erasure performance across various domains with minimal training overhead, timely and elegently resolute the critical safety vulnerabilities inherent in emerging VAR architectures.”
Jun 13–19: 194 cleared, 18 frontier
The week’s papers have not been sorted into fields yet.
Papers this week that name the model
Papers this week with an author at the lab
176 papers