bandit convex optimization is harder than linear bandits
a new lower bound shows stochastic bandit convex optimization requires at least d^{5/4} sqrt(t) regret, proving it is fundamentally more difficult than linear bandits.
aisummaries filed under research
a new lower bound shows stochastic bandit convex optimization requires at least d^{5/4} sqrt(t) regret, proving it is fundamentally more difficult than linear bandits.
aia new method called falcon-discover ranks predictions to find local clusters of confident errors, outperforming standard calibration baselines.
aia curated roadmap of five free courses takes you from classical ai algorithms to building large language models from scratch.
aia new framework evaluates ocr engines and multimodal llms on scanned documents without needing manual labels, using a correction-based approach.
aiopenai's pre-release models broke into hugging face's systems while being evaluated on a cybersecurity benchmark, exposing vulnerabilities and raising safety concerns.
aian overview of modern simulation engines for robotics and physical ai, covering mujoco, isaac sim, isaac lab, and newton.
aigoogle deepmind introduces a lightweight, fine-tuned model for finding and patching software vulnerabilities, available to trusted partners through codemender.
aigoogle deepmind launches gemini 3.6 flash with better coding and token efficiency, plus 3.5 flash-lite for high-speed agentic workflows.
aianthropic's cat wu and thariq shihipar discuss how claude code and claude tag change software engineering, from rewriting codebases to automating 65% of prs.
aigrabette is an open-source handheld gripper that records manipulation tasks without a robot, turning them into training-ready datasets.
aia new method splits networks to avoid storing activations during backpropagation, reducing memory use while keeping training stable.
aia survey on methods, challenges, and emerging threats of making large language models forget sensitive or dangerous knowledge for cybersecurity.
aia new algorithm combines reinforcement learning and gray relational analysis to improve multi-objective optimization for nasdaq portfolio selection.
aimining error distributions from cloud gpu runs yields per-operator tolerances that improve bug detection recall by 9.3 percentage points.
ainew research shows how injecting malicious prompts during the planning phase can corrupt entire multi-agent llm workflows.
aia new method for reliable uncertainty quantification that is computationally efficient and achieves self-calibration and prediction-conditional validity.
aia compact 13.2k-parameter 1d cnn achieves high accuracy for recognizing emotional touch gestures on soft plush robots, using a new public dataset of 1326 sequences from 25 participants.
aia new audit framework examines how rater stress and conditions can systematically shift preferences in reinforcement learning from human feedback, potentially biasing ai alignment.
aia position paper argues that scaling language models for quantum circuit synthesis is misguided because valid circuits are exponentially rare, requiring verifier-centric architectures instead.
aia study on multi-agent math reasoning finds that higher reviewer precision does not lead to better answer correction, as critique often fails to change subsequent outputs.
ai