AI
Jailbreak prompts can still push chatbots to produce harmful content, even after safety training. Many defenses either miss sophisticated attacks or over-block harmless requests. This paper finds a useful clue: during generation, models carry latent safety signals that spike when content turns risky, but those signals get overridden by the
When AI agents team up, surprising things happen Large language models don’t start from scratch. They arrive preloaded with vast knowledge and social priors, and they adapt quickly from context. When many such agents interact, their group behavior can surprise us—for better or worse. A new paper argues
AI
AI that reads privacy policies so you don't have to Privacy policies are long, legal, and hard to compare. LADFA is a new AI framework that turns those walls of text into a clear map of how companies collect, use, store, and share your personal data. How it
New paper by Philip Resnik asks a simple question: are today’s language models (like ChatGPT) actually models of how the human mind works? * Implementation level: No. Brains and LMs are built and operate very differently. * Algorithmic/representational level: Weak support. We lack good evidence that LMs use the same
LLMs turbocharge ontology development Ontological Knowledge Bases (OKBs) organize domain know-how, but hand-crafting them is slow and brittle. This research shows how Large Language Models can help experts build and refine OKBs faster—and with more consistency. The team proposes a structured, iterative workflow that uses LLMs to: * extract and
AI
AI agents can be powerful—and unpredictable. AgentGuardian is a new security framework that keeps them on-task by learning and enforcing access rules tailored to each agent. How it works: * Staging phase: It watches the agent run in a controlled setting, logging execution traces and typical inputs to learn what
AI
Most top video AIs are locked up. Molmo2 opens the door: open weights and open datasets, built to understand videos and ground that understanding by pointing to and tracking objects in the pixels. * Data you can build on: 7 new video datasets and 2 multi-image sets, including rich video captions,
Can AI make architecture students better designers? A controlled study of 36 students compared solo work to a second round with either Generative AI or a repository of past projects. Experts rated designs; students reported confidence and mental effort. What they found: * No overall performance boost from GenAI versus the
AI that transcribes drums—no paired audio required Most drum-transcription AIs need huge, matched audio–MIDI datasets. Those are scarce. Synthetic stand‑ins often sound cheap, creating a domain gap. We flip the script. With a semi‑supervised pipeline, we automatically curate a large, diverse library of high‑quality one‑
Tiny pixels, big clues for Chinese AI Chinese characters pack meaning and sound into their shapes. This study asks: can AI learn better by seeing characters instead of just looking up IDs? * Using tiny 8x8 grayscale images of single characters, the model hits 39.2% accuracy—on par with 39.
AI
Smaller, smarter music AI Foundation models are powerful—but huge and pricey to run. This study shows how to keep music understanding strong while trimming model size and compute. * What’s new: A lean architecture that swaps heavy self‑attention for Branchformer + SummaryMixing, plus a simple random quantizer to learn
AI
New AI that keeps creativity: DPWriter LLMs trained with reinforcement learning often play it safe, shrinking the variety of their stories. DPWriter flips the script by planning before writing. It breaks generation into semi-structured steps, then uses Diverse Planning Branching to explore multiple, intentionally different routes. A group-aware diversity reward