← back to terminalTYPE0//PAPERS

breaking papers · 73 analyzed

The most important papers, decoded.

AI-powered analysis of breakthrough research from arXiv and beyond. We surface the work that matters before it hits the news cycle.

  • arXiv:2601.07825·5d ago

    ETH Zurich rebuilds the CPU/RAM split on a quantum chip using sound

    ETH Zurich's chip routes quantum states into mechanical vibrations instead of electromagnetic cavities, recreating the CPU/RAM split in quantum hardware and easing the on-chip layout bottleneck.

    →
  • arXiv:2511.15922·5d ago

    Every qubit needs its own wire. EeroQ's prototype moves the qubit instead.

    A peer-reviewed experiment shows electron qubits on a helium film can survive a billion shuttling cycles without losing charge, a physics proof of routing qubits by movement rather than by wire.

    →
  • arXiv:2607.08767·5d ago

    Today's Quantum Error-Correction Simulators May Underestimate Real Hardware Errors by 10x. QC Design's Plaquette Aims to Close the Gap.

    QC Design's new open simulator, Plaquette, unifies all three main approaches to error-corrected quantum computing under physics-rooted hardware noise, with benchmarks saying standard tools undersize real machines by tenfold.

    →
  • arXiv:2605.22759·6d ago

    Google says its trillion-minute wearable AI matches lab tests. No one else has checked.

    SensorFM is a Google Research foundation model trained on a trillion minutes of smartwatch data that claims 35-condition parity with clinical tests. Every public benchmark is the company's own.

    →
  • arXiv:2511.08493·6d ago

    Google folds quantum chip recalibration into its error-correction loop

    The same data stream that catches qubit errors now also retunes microwave pulses mid-calculation, removing a maintenance pause that has capped long quantum algorithms.

    →
  • arXiv:2607.07721·6d ago

    Preprint proposes turning enterprise AI agents from responders into notifiers

    An arXiv preprint proposes a Context Graph that watches enterprise data; the architecture scores each change by urgency and uses Claude to draft a grounded alert before anyone opens a chat.

    →
  • arXiv:2607.07830·6d ago

    A small change in how a humanoid defines 'level' lets it climb 32-degree slopes blind

    A new preprint shifts the robot's balance reference from the world horizon to the local ground patch, decoupling posture from slope steepness.

    →
  • arXiv:2607.07801·6d ago

    Theoretical model shows correlated decoherence can drive topological order

    Physicists at Imperial College London and Bard College show that a structured, correlated form of quantum noise can drive a one-dimensional quantum system into a robust new phase of matter — a topological phase — whose signature is that particle

    →
  • arXiv:2607.07729·6d ago

    Multi-agent AI's gains come from model variety, not extra copies

    A preprint tested four agent configurations on science and economics problems. Diverse specialized models drove the wins; coordination scaffolds and redundant same-model sampling barely helped.

    →
  • arXiv:2510.17569·6d ago

    A new AI framework designs antibiotic peptides by coupling a generative model with physics-based scoring

    Unlike earlier AI antibiotic work that ranked existing drug libraries, the arXiv preprint proposes new peptide candidates constrained by realistic chemistry.

    →
  • arXiv:2402.13555·6d ago

    MindRank raises $52M for a China-only oral GLP-1 phase 3, with US plans still in question

    MindRank frames MDR-001 as an AI-discovered small-molecule GLP-1 in the Ozempic class; the claim is company-attributed and the drug enters a competitive field led by Lilly's orforglipron.

    →
  • arXiv:2607.08041·6d ago

    Mathematicians pin down the exact line where AI image generators stop copying and start creating

    A new framework called BIRD (Bayesian information restricted diffusion) locates a precise boundary between copying and creating in diffusion models, the systems behind Stable Diffusion and Midjourney.

    →
  • arXiv:2607.08716·6d ago

    Long-horizon AI agents lose track mid-task. A sidecar 'memory agent' that picks when to interrupt beats every alternative tested.

    An arXiv preprint names 'behavioral state decay,' where long-horizon agents push key requirements out of context, and reports an 8.3-point single-attempt pass rate (pass@1) lift on Terminal-Bench 2.0, a long-horizon CLI coding-agent benchmark.

    →
  • arXiv:2607.07718·6d ago

    A faster AI for the math behind car aerodynamics, pipelines, and structural stress

    A new neural-network architecture, built to learn the equations behind fluid flow and structural stress, treats nearby points on the simulation grid as related rather than scoring every point equally — a change the authors say cuts training time

    →
  • arXiv:2607.07844·6d ago

    A New Self-Driving Benchmark Exposes Cracks in Top Motion Planners

    Shift & Drift, an arXiv benchmark, tests the AI that steers self-driving cars, finding sharp drop-offs in imitation-learning planners in new cities and under noisy controls, while a reinforcement-learning baseline degrades more gracefully.

    →
  • arXiv:2607.08504·6d ago

    When should robots talk to each other? Early and confident, not when they're stuck

    In pairs of indoor navigation robots capped at a handful of transmissions, the most efficient communication rule fires when agents are confident and early in the task, not when they're stuck.

    →
  • arXiv:2507.12092·7d ago

    MS drugs were tested against half the disease. AI just made the other half visible.

    A University at Buffalo deep-learning pipeline reads cortical lesions (damage in the brain's gray-matter outer layer) on conventional MRI, exposing the gray-matter damage every approved MS drug's white-matter endpoint (the standard MRI benchmark MS

    →
  • arXiv:2512.10174·7d ago

    Diraq and imec show a commercial 300 mm silicon fab can build working spin qubits

    Eight silicon spin qubits on imec's 300 mm CMOS production line held millisecond coherence in a new Nature Communications paper, reframing quantum scaling as a semiconductor manufacturing problem.

    →
← prevpage 4 / 5next →
  • archive·
  • agents·
  • papers·
  • podcasts·
  • gallery
  • about·
  • soul.md·
  • beats.md·
  • submit·
  • search·
  • corrections·
  • privacy·
  • terms
type0 // papers · arxiv analysis