#Paper/Research

AIHarvard physicist Matthew Schwartz argues that LLMs are poorly matched to science when used as human-style collaborators, so he built a toolkit for exact quantitative calculations. Working with Claude, the approach surfaced connections to ecology, population genetics, and a dozen other fields, with domain experts steering it toward interesting questions.

AIOdyssey introduces PROWL-2, a recursive loop that delivers up to 91% relative gains over the StarCraft world-model baseline. The post also reports stronger robot coordination in simulation.

AIGoogle Gemma relays a StudentBench study reporting that AI tutors matched expert human tutors on immediate GRE learning gains. The author reports 2,383 students and a cost of 7 cents per AI tutor hour versus $75 for an expert human hour. The post also says the top AI tutor beat expert human tutors on average in 5 of 7 academic topics, and that the data and paper are publicly available.

AIGoodfire reports that its method catches more unsafe biological requests than frontier model safeguards while dramatically reducing false positives. The claim is illustrated by a plot in the first tweet of the thread.

AIGoodfire Research developed sequence-aware monitors using protein language model embeddings to flag concerning biological sequences in dual-use AI agent tasks. On a custom benchmark, the monitors outperformed frontier model safeguards with fewer refusals on benign requests, and they held up better against paraphrasing and fragmentation attacks. The paraphrase results rely on in-silico estimates and do not establish whether the redesigned proteins keep biological activity, and the monitors run in milliseconds per sequence.

Why it matters: The post gives a concrete benchmark setup and fragmentation results, showing how sequence embeddings can separate dual-use biology requests that task-based safeguards handle poorly.

AIZyphra published a paper and blog explaining how local mixing encodes relative position in global NoPE attention models. The work, titled "How Local Mixing Encodes Relative Position in Global NoPE Attention," is available on arXiv and on Zyphra's website.

AIModels using Kimi Delta Attention show a recency bias, as the mechanism controlling how much earlier information is kept shapes memory. As new information mixes into that memory, nearby words share more information, which gives the model clues about how far apart words are.

AISara Hooker shared a full technical report on a method for creating datasets from zero seed data, linked via alphaXiv. She also pointed readers to an interactive tool at adaptionlabs.ai where users can begin inventing datasets.

AIAmazon Science describes a graph-centric approach in which a network digital twin graph and cascaded graph algorithms, orchestrated by an agentic AI layer, identify root causes in complex network failures. The approach was demonstrated with NTT DOCOMO at the Mobile World Conference, achieving root cause analysis in minutes on commercial networks. The article traces how graphs evolved from topology models to active reasoning substrates for agents.

AIUnder equal time budgets and the same frontier LLM backbone, a single session of a minimal-harness coding agent with read, write, and bash primitives matched open-source state-of-the-art autonomous machine learning engineering harnesses. Apple researchers found the added orchestration and retrieval machinery redundant in large-scale ablation studies, pointing to the backbone model as the main driver of performance. They conclude that hand-crafted harnesses around strong models yield poor returns on current MLE benchmarks.

AIApple researchers introduced RLTL;DR, a reinforcement learning method in which an agent writes its own one-line insight after each failed attempt and learns to map tasks to those insights. On challenging tool-calling and coding datasets filtered to Pass@128 = 0, standard GRPO training of a Qwen 3.5 9B Thinking policy stayed at 0% to 1% Pass@1, while RLTL;DR reached 14–31% with insights in context and 12–13% without them at evaluation. A compact variant, SFTL;DR, trained on just 4k task-insight tuples recovered nearly the full performance of RLTL;DR.

AIA flu forecasting model built with Google AI ranked first among 39 eligible models in the CDC's FluSight 2025-26 season evaluation for predicting U.S. flu-related hospital admissions. The model was developed using Empirical Research Assistance (ERA), an AI tool that generates optimization algorithms, and ERA's underlying technology is now available to trusted testers.

AIRetrieval systems that split long documents into chunks lose surrounding context. Contextual embedding models address this by encoding the entire document once and pooling chunk vectors afterward. They are usually trained using one gold chunk per query.

AIGoogle DeepMind reports that AI-designed proteins can be synthesized and watermarked using its new SynthID Bio method, published in Nature. The team says the work is a step toward biosecurity in AI-driven biology and is open-sourcing the SynthID Bio tools for the research community.

AIMicrosoft Research intern-developed machine learning pipeline forecasts location-specific geomagnetic risk for 66,935 substations in the continental United States. It combines solar-wind observations, AE and Dst forecasts, geological conductivity and grid data to estimate risk 30 to 60 minutes ahead. The pipeline detected nearly 80% of major space-weather events during the evaluation period.

AIYandex Research says it is releasing AsyncLLM, a framework that lets pretrained LLMs observe, reason, and act concurrently with no additional training. The paper, code, and demos are published on Hugging Face, GitHub, and the project website.

AIAnthropic's research rates how well present-day robots can perform US job tasks, finding they can do 74% of physical tasks, or 34% of working hours, mostly in limited settings. Robots are cost-competitive for only 0.3% of job tasks, and at a 3% annual price decline it would take about 40 years to reach 10%. The report also finds robot-exposed jobs tend to pay less and be more physically demanding than LLM-exposed jobs.

Why it matters: The report separates current robot capability from cost, showing that physical automation is technically broad but economically narrow for now.

AINumerical differences between a rollout engine and a trainer can make reinforcement learning collapse even when algorithm and data stay identical. In a GLM 5.2 experiment, reward fell from about 0.9 to under 0.2 around step 20 without alignment, while aligned numerics kept reward stable over 25 steps. A Qwen3.5-MoE investigation traced a significant mismatch to how expert outputs were combined, and router replay alone was judged insufficient.

AIApple researchers systematically tested LLM conditioning methods and found efficient activation steering often degrades fluency. Steering is far less effective on instruction-tuned models than base models, while prompting and full supervised fine-tuning work for concept injection but are weaker at concept removal. Cheap textual metrics correlate highly with costly LLM-as-judge scores.

AIGoogle Developers Blog describes how Sparse VideoGen (SVG) routes video diffusion attention heads into spatial or temporal sparse masks and implements them as custom JAX and Pallas Splash Attention kernels on TPU v6e. In isolated single-chip tests with 75.6K tokens and 10 heads, the sparse variants retain about 38.87% of query-key pairs. The article argues that theoretical sparsity must be converted into hardware tile skipping to yield real speedups.

AIGoogle Research introduced Diffusion Controller, a framework that treats image generation as a continuous control problem rather than separate inference-time guidance and fine-tuning fixes. Its lightweight add-on "steering damper" network keeps the base model frozen and works on black-box or gray-box models, and it outperformed the industry standard on human preference matching. In a Stable Diffusion v1.4 test, the fully unlocked version achieved a 90% win rate over the baseline.