AI News

‹All dates

413

EmbodiedSmith: scaling embodied data via recursive self-improvement in simulation

An arXiv paper introduces EmbodiedSmith, a framework for scalable embodied data generation through recursive self-improvement (RSI) in simulation, unifying asset, scene and task generation with autonomous, language-driven customization. Its core is an agentic refinement loop in which scene generation anticipates downstream task requirements while task generation guides targeted scene edits, improving task-generation success including for long-horizon tasks. The framework also supports mobile manipulators, humanoids and dexterous hands, plus deformable objects and fluids; the authors report downstream policy experiments showing that greater data diversity improves generalization.

Hugging Face · Papers·2d

423

Research

Speculative execution cuts on-device voice agent latency from 5.79s to 4.60s

An arXiv paper proposes speculative tool execution for on-device cascaded voice agents: a Predictor module anticipates tool calls from partial ASR hypotheses, runs them speculatively and caches the results, which are then injected into the LLM prompt for faster responses. A rule-based validation step filters cached results invalidated by user self-corrections, and the LLM can still issue tool calls directly, so worst-case latency stays bounded by the serial baseline. In live measurements on a fully implemented Android voice assistant, median time-to-first-audio fell from 5.79s to 4.60s and the standard deviation from 3.49s to 2.81s.

Hugging Face · Papers·2d

433

Research

MediateRec benchmark tests personal-agent mediation of cross-platform recommendations

The paper formalizes a paradigm called Personal-Agent Mediated Recommendation: a platform recommender ranks a candidate set from platform-local information, and a personal LLM agent then uses user-authorized cross-platform history to mediate that ranking into a final top-K slate. The authors introduce MediateRec, a benchmark with scalable proxy cross-platform environments plus a real cross-platform test under a controlled platform-agent information boundary, and propose Personal Attribution Mediation Optimization (PAMO), which counterfactually masks cross-platform history to estimate personal mediation support and reallocate rank-aware advantage mass. Experiments show mediation yields meaningful platform corrections, but even strong proprietary LLMs introduce non-negligible harmful overrides; PAMO beats matched outcome-only RL on seen and unseen target platforms and on the real test, with a better rescue-harm balance.

Hugging Face · Papers·2d

443

Research

Attacca: goal-directed control for long-horizon embodied agents

An arXiv paper introduces Attacca, a method for training visual goal-conditioned policies for long-horizon embodied agents. It uses context-decoupled goal sampling to pair each demonstration with a class-compatible masked goal image from another world, adds a target-mask prediction head for dense current-view grounding, and conditions the policy on Search, Approach and Interact phases. On short- and long-horizon Minecraft tasks, the authors report 39.0–47.5% clean success, a 1.7–2.4x gain over the strongest baseline, and 54%, 30% and 28% completion on long-horizon tasks, up to a 7x improvement.

Hugging Face · Papers·2d

450

Research

AI Reconstructs Viewed Images From Brain Scans

Researchers at Israel’s Weizmann Institute of Science developed an AI system that uses high-resolution fMRI data to reconstruct images people are viewing, combining brain decoding with an image diffusion model. The team trained it on data from eight participants who viewed about 9,000 images each, and reports that the system can be calibrated to a new participant with about one hour of data rather than the roughly 40 hours required by earlier approaches.

MMIT科技评论中文·2d

460

Research

Caltech team reports AI-found Euler singularity candidate

A Caltech team led by Anima Anandkumar reports using physics-informed neural networks to search for a self-similar singularity candidate in the unforced 3D Euler equations on R3. The reported optimization converged on a scaling exponent near 0.5, but the result is a numerical candidate rather than a rigorous proof; the Clay Mathematics Institute still lists the related problem as unresolved.

新智元·2d

470

Research

VA-Bench Finds a Gap Between Spatial Understanding and Robot Execution

The VA-Bench paper evaluates 12 multimodal models in closed-loop robot tasks spanning observation, reasoning, action, and revision. The source reports that leading models achieved near-perfect target localization and action-semantic scores, but complete-task success remained around half, with online correction, fine-grained control, active perception, and bimanual coordination as major weaknesses.

机器之心·3d

480

Research

Qwen3.8 27B sums big numbers in words, hitting 167/169 with reasoning on

Simon Willison re-ran an experiment Colin Frasier first tried two years ago with GPT-4o: have a model compute large sums but return the answer in words. He ran it on local hardware (a DGX Spark), using a Codex Remote session (GPT-6 Astra) to write and execute the test with Qwen3.8-27B-Q4_K_M.gguf. With reasoning disabled he sampled 30 attempts per cell; with reasoning enabled each run took so long that he used one sample per pair, and the model got 167 of 169 attempts right.

SSimon Willison's Weblog·3d

490

Research

Eric Betzig Warns AlphaFold Alone Cannot Solve Drug Discovery

Nobel laureate Eric Betzig argued in a podcast interview that using AlphaFold protein structures alone for drug discovery is unlikely to succeed, because cells are dynamic, crowded, multiscale systems. He proposed combining live-cell 4D/5D imaging, self-supervised vision Transformers and zebrafish models to study drug effects from molecules to whole organs, while also criticizing academic incentives built around papers, grants and peer review.

MMIT科技评论中文·3d

500

Research

2026 Nobel Prize honors optogenetics pioneers

QbitAI reports that Karl Deisseroth, Peter Hegemann, and Georg Nagel received the 2026 Nobel Prize in Physiology or Medicine for discoveries involving light-gated ion channels and optogenetics. Their work connected light-sensitive proteins from green algae with precise, millisecond-scale control of selected neurons, helping neuroscience move from observing correlations to testing causal links between neural activity and behavior.

量量子位（原生 RSS）·2d

510

Research

Apple paper studies how users negotiate ontological boundaries in personal sensing systems

Apple Machine Learning Research and Stanford University authors published "Negotiating Ontological Boundaries in User-Authored Personal Sensing Systems." They built two open-ended Wizard-of-Oz probes that let participants experience training a personalized machine learning system on phenomena they define themselves, then ran a week-long exploratory study. The authors identify four sites of ontological boundary negotiation — the boundaries of a phenomenon, the subject as part of relations, what counts as signal versus noise, and the objectivity of data — and offer design starting points for supporting such negotiation.

AApple Machine Learning Research·3d

That's everything.

← Previous