Skip to content
Only First-party#Papers / research
November 13Friday
  1. Microsoft Research22

    Microsoft Research Focus Edition #98: AI Translation, KLS Conjecture Proof, and Faster Coding Agents

    Microsoft Research Focus Edition #98 highlights AI advances bringing universal translation closer to reality and a new proof resolving the 31-year-old KLS conjecture in high-dimensional geometry. The edition also covers CompactionBench and APEC, which cut coding-agent context compaction costs by up to 25.4% and execution time by 9.6%, plus the Latent Core Tokenizer, which improved tokenization across 104 languages.

November 12Thursday
  1. OpenAI Alignment Blog58

    OpenAI uses automated red teaming to improve fuzzy robustness in GPT-6 Astra and Sol

    OpenAI researchers describe how automated red-teaming, using a GPT-5.6 Sol family reasoning model as attacker against GPT-5.4 and GPT-5.5 defenders, generated synthetic jailbreaks that were used as RL training data for GPT-6 Astra and Sol. On fixed jailbreaks from prior attacks against GPT-5.4 and 5.5, GPT-6 Astra answered 91.5% safely on cyber versus 59% for GPT-5.6 Sol, and it stayed more robust across all attacker budgets in an adaptive multiturn eval. OpenAI reports the robustness training did not raise refusals of benign tasks, citing a Pareto improvement on safety and helpfulness in the GPT-6 Astra system card.

  2. Apple Machine Learning Research38

    Theoretical Limits of Language Model Alignment

    Researchers from Apple Machine Learning Research derive the information-theoretic limits of KL-regularized language model alignment, giving a closed-form expression for maximum expected reward gain under a fixed KL budget that is governed by a Jeffreys divergence term rather than the √KL used in prior analyses. They show the gap between ideal and proxy alignment (reward hacking) grows with reward error and shrinking KL penalties, and prove reward ensembling mitigates it. On safety and summarization tasks, best-of-N closely approaches the theoretical limit while PPO and GRPO remain substantially suboptimal.

  3. Google Research58

    Google Research uses wearables to build CKM risk profiles and personalized coaching

    Google Research introduced an investigational framework that turns consumer wearable data into a coachable health age and simulates personalized 12-week what-if health trajectories. The SensorWM world model was pretrained on 2.28 million person-weeks of de-identified Fitbit data from roughly 100,000 users and forecasts 20 physiological markers under different step, sleep and cardio routines. In a blinded study, lifestyle coaches chose the counterfactual-grounded plan as best overall in 71.4% of evaluations, and physicians rated 99.2% of plans within safe exercise intensity limits; the authors note the models are research prototypes, not clinical diagnostic tools.

  4. Google Developers Blog58

    Google Agent Anomaly Detection scores on five public agent-security benchmarks

    Google ran its Agent Anomaly Detection, in Private Preview on Gemini Enterprise Agent Platform, against five public agent-security benchmarks it did not write, scoring 1,774 sessions. It flagged 87% of harmful instructions the agent actually carried out, with false alarms on 2% to 16% of benign sessions, and caught only 4 of 18 sessions where poisoned long-term memory drove the agent to act. The tests used an agent built with the Agent Development Kit (ADK) on gemini-2.5-flash, covering AgentDojo, InjecAgent, Agent Security Bench, AgentDyn and AgentHarm.

November 11Wednesday
  1. inclusionAI Models40

    inclusionAI Releases ZoomGain-9B and ZoomGain-4B Models with ZoomGainBench and RL Training Data

    inclusionAI released the ZoomGain-9B and ZoomGain-4B vision-language model checkpoints, alongside the ZoomGainBench evaluation benchmark and ZoomGain RL training data. ZoomGain mines global-to-zoom perception gaps to build fine-grained visual supervision, and ZoomGain-9B reached superior performance on multiple fine-grained and general perception benchmarks. ZoomGainBench contains 1,000 questions over 941 images, while the RL dataset holds 9,000 training records and 7,713 source images.

  2. inclusionAI Models38

    inclusionAI Releases ZoomGain-4B and ZoomGain-9B with ZoomGainBench and RL Training Data

    inclusionAI released the arXiv paper, ZoomGainBench evaluation benchmark, RL training dataset, and ZoomGain-4B/ZoomGain-9B model checkpoints. The best of 28 models scored 61.08 on ZoomGainBench, while ZoomGain-9B reached superior performance on multiple fine-grained and general perception benchmarks. ZoomGain mines global-to-zoom perception gaps to build fine-grained visual supervision for vision-language models.

  3. Microsoft Research75

    Microsoft researchers describe Lazarus, a backdoor that reprograms dormant neurons in AI agents

    Microsoft researchers have described Lazarus, a backdoor technique that reprograms fewer than 10 dormant neurons in an LLM so an agent built on it emits attacker commands when a hidden trigger appears, with no retraining required. The modified model still passes standard evaluations and behaves normally until the trigger, which can be as simple as a date change, and the agent then runs the downloaded code with whatever access it was given. The authors say detection requires diffing against the original weights, and Microsoft Foundry already ties open-weight models to their publishers and scans their containers, while red-teaming harnesses, agent-based weight scanning and signed models with tamper-evident provenance are in development.

    Why it matters: Microsoft researchers show that reprogramming fewer than 10 dormant neurons can backdoor an LLM agent without retraining, which makes weight provenance and integrity a practical security requirement.

November 10Tuesday
  1. Google DeepMind82

    Google DeepMind introduces AlphaProof Code, formally verifying Signal's cryptographic code

    Google DeepMind researchers used AlphaProof Code, a multi-LLM agentic framework, to formally verify key security properties of the actual code underlying the Signal protocol. Agents powered by Gemini Carbon generated over six million lines of Lean, and human experts reviewed only about one percent of the codebase; the verification took four weeks, a task that historically takes expert teams years. When two previously fixed bugs were reintroduced into an isolated version of Signal's code, the system produced machine-checked proofs that the buggy versions were insecure, and DeepMind is open-sourcing its formal verification artifacts.

    Why it matters: Google DeepMind's multi-agent framework formally verified Signal's deployed cryptographic code in four weeks, a task that historically takes expert teams years.

  2. OpenAI Alignment Blog60

    OpenAI studies what affects CoT monitorability across the model lifecycle

    OpenAI researchers examined how pretraining, architecture, reinforcement learning and model-generated data affect two proxies for chain-of-thought monitorability: no-CoT capability and CoT controllability. They report that no-CoT capability tracks lower base-model perplexity smoothly, that CoT controllability rises during RL even without process supervision beyond length constraints and final-answer grading, and that controllability can be passed to a student model through SFT on a teacher's rollouts. The authors caution that both proxies are imperfect and that models may become harder to monitor through their CoT as capabilities scale.

    Why it matters: OpenAI's lifecycle study links lower pretraining perplexity and RL scaling to weaker CoT monitorability, offering a concrete frame for how training choices shape oversight risk.

  3. Apple Machine Learning Research34

    Weighted State Souping for Efficient Long-Context Retrieval

    Apple researchers and Harvard collaborators propose weighted state souping, a method that learns query-dependent weights for recombining cached SSM state encodings, improving long-context performance on single- and multi-hop document QA, needle-in-a-haystack retrieval, variable tracking, and tool use. A sparse variant achieves near-constant encoding cost with respect to context length while preserving or sometimes improving performance. The paper was accepted at the PALM workshop at NeurIPS 2026.

  4. Apple Machine Learning Research38

    Apple Study: Gating Mechanism Explains Why SSMs Memorize Instead of Learning In-Context

    An Apple and Harvard study shows that the gating mechanism in State Space Models (SSMs) causes them to first learn an in-weights "memorization" solution, delaying or even preventing convergence to correct in-context learning. This occurs even when the architecture and memory capacity impose no fundamental limits. Gating, however, often improves generalization to long sequence lengths.

  5. Apple Machine Learning Research31

    Apple study evaluates LLM judges for personalized writing style assessment

    Apple researchers tested how well LLM judges assess whether generated text matches a user's preferred writing style, generating text with four LLMs across three long-form writing tasks and comparing judge annotations against human pairwise labels. Judge quality correlated only weakly with general LLM ability on MMLU (Pearson's ρ ≤ 0.2) and varied by writing task and evaluation criteria, and paired comparisons proved more consistent than independent scoring. The strongest LLMs did not most reliably reproduce human evaluations, possibly due to exaggerated sensitivity to subtle details.

  6. Goodfire Research62

    Goodfire studies Qwen3.6-35B-A3B neurons as an interpretable basis

    Goodfire Research published a study arguing that individual MLP neurons in Qwen3.6-35B-A3B are more interpretable than assumed, based on sparsification, attribution tools and research agents. Ablating the 92.2% weakest MoE neuron activations per forward pass raised language model loss by only 2.9%, and 69% of neuron poles had a single mode responsible for at least 90% of their causal effect. Natural-language neuron descriptions let a judge model predict firing with 95% accuracy against random text and recover 73% of ablation damage through simulation.

    Why it matters: Goodfire's study of Qwen3.6-35B-A3B neurons argues that strong activations alone carry most of the model's computation, offering a concrete alternative to feature-dictionary interpretability.

November 9Monday
  1. Hugging Face Blog38

    NVIDIA and Elith Release Nemotron-Personas-Finance-Japan Synthetic Dataset

    Elith and NVIDIA released Nemotron-Personas-Finance-Japan, an open synthetic persona dataset for Japan's financial sector built on official government statistics. It contains 9M personas (1M records × 9 personas) across 50 fields and ~1.5B tokens, generated with NeMo SDG-PGMs and NeMo Data Designer, and is available under CC BY 4.0 for commercial use.

  2. Hugging Face Blog40

    HOPE: Higher-Order Pruning of Experts in Mixture-of-Experts Language Models

    Researchers introduce HOPE, a second-order expert pruning method for Mixture-of-Experts language models that accounts for pairwise interactions between co-activated experts instead of scoring each expert independently. At 50% pruning, HOPE achieves the best average rank of any method, with gains of up to +6.1% on agentic coding tasks over the next-best pruning method. The work targets the memory bottleneck in models such as Qwen3.5-122B, where expert MLPs take up 95% of a ~250 GB footprint.

  3. Anthropic · Claude.dev80

    Anthropic: 1,000 Claude Fable 5.2 agents reproduce Fermat's Last Theorem formalization in 28.7 hours

    7 hours without the Prove2Me platform or researcher steering used in Anthropic's September run, writing a proof one-seventh as long and using one-third as many output tokens. Each agent worked in a network-isolated sandbox with a classifier checking every shell command and file edit plus an offline monitor, and across more than a million tool calls none met the bar to be blocked.

    Why it matters: Anthropic's 1,000-agent run reproduced the Fermat's Last Theorem formalization without Prove2Me or a researcher, showing how sandboxing and monitoring bound a self-organized agent team.

  4. Berkeley AI Research22

    BAIR at CoRL 2026: Berkeley Robot Learning Papers, Orals and Keynote

    UC Berkeley's BAIR is presenting 33 main-conference papers, 4 late-breaking posters, 3 orals and 7 spotlights at CoRL 2026, held November 9–12 in Austin, Texas. Professor Negar Mehr delivers an Early Career Keynote on how robots learn to interact and coordinate with others. Work spans embodied memory for vision-language-action models, dexterous manipulation scaling with egocentric human data, and agentic robot self-improvement.

  5. inclusionAI Repositories38

    ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision

    ZoomGain constructs questions about a full image from visual details that only become clear when zooming in, using this global-to-zoom perception gap as supervision for vision-language models. The release includes the arXiv paper, the ZoomGainBench benchmark (1,000 questions over 941 images covering attribute recognition, counting, and OCR), 9,000 RL training records over 7,713 source images, and the ZoomGain-4B and ZoomGain-9B checkpoints. The best of 28 models scored 61.08 on ZoomGainBench, while ZoomGain-9B reached superior performance on multiple fine-grained and general perception benchmarks.

  6. Anthropic Research71

    Anthropic tests Claude Fable 5.2 on real-world electronics design

    Anthropic reports that Claude Fable 5.2 designed three electronic devices, a speakerphone, a voice-assistant hub and a handheld virtual pet, from minimal prompts, and that Diode Computers built working prototypes from its design files without circuit fixes. On Diode's internal PCB Gym benchmark, Fable 5.2 scored 69% versus 25% for Fable 5, and it reached 83.5% on the public BenchCAD 2.1, nearly double Claude Fable 5.1. The devices remain prototypes that have not been through electrical validation, antenna tuning, thermal testing or certification, and Claude was not connected to test equipment or manufacturing machines.

    Why it matters: Anthropic's own account of Claude Fable 5.2 designing three working electronic devices shows how far models have moved from partial PCB layouts to end-to-end hardware prototyping.

November 6Friday
  1. Hugging Face Blog58

    Ai2 releases ToyBlocks, an open simulated block-manipulation world for robot learning

    Ai2 released ToyBlocks, an open simulation framework built around a robot arm and blocks on a tabletop, as the first of its FoundationWorlds for controlled robot learning and evaluation. The framework auto-generates skills and demonstrations via RL and motion planning in Isaac Lab, reaching up to 24x real-time on a single GPU, and ships with 85,336 long-horizon demonstrations covering nearly 1,600 hours and 144 million frames. In its experiments, ManiFlow's atomic-skill success was 80.0% in simulation and 81.1% on a real Franka FR3, while the Molmo 2 plus ManiFlow system succeeded in 55.5% of simulated and 50.0% of real-world episodes.

  2. Ai2 · Allen Institute for AI58

    Ai2 releases ToyBlocks, a controlled simulated world for robot learning and evaluation

    Ai2 released ToyBlocks, an open simulation framework built around a robot arm and blocks on a tabletop, as the first of its FoundationWorlds for controlled robot-learning research. ToyBlocks auto-generates tasks and demonstrations via RL and motion planning in Isaac Lab, reaching up to 24 times real-time data generation on a single GPU, and ships with 85,336 long-horizon demonstrations covering nearly 1,600 hours and 144 million frames. In real-world tests on a Franka FR3, ManiFlow's atomic-skill success was 80.0% in simulation and 81.1% on hardware, while the Molmo 2 plus ManiFlow system succeeded in 55.5% of simulated and 50.0% of real episodes.

  3. vLLM Blog77

    REINFORCE Zero: Kernel Alignment Enables Stable Async RL at Policy Lag 64, Extends to DeepSeek-V4.1 and Kimi K3.1

    NVIDIA Research and Inferact's REINFORCE Zero paper shows that aligning rollout and trainer kernels lets unclipped token-level importance sampling correct the remaining weight lag, training stably for 20,000 updates at policy lag 64 and reaching 2.40x the training-step throughput of synchronous training with aligned kernels. With standard kernels, the median rollout-to-learner KL rises 83.33x across the run and online AIME24 pass@1 falls from 34.27% to 13.96%, while a sequence gate stabilizes training but rejects 24.48% of sequences by the last 1,000 updates. The zero-mismatch setup now covers DeepSeek-V4.1-Flash, Kimi K3.1 on release day, and DeepSeek-V4-Flash and Kimi K3.1 on AMD MI355X, with code in Inferact/zero-mismatch-rl and NVIDIA-NeMo/labs-molt.

    Why it matters: NVIDIA Research and Inferact split the async RL rollout-learner gap into weight lag and kernel mismatch, showing that aligning kernels lets unclipped importance sampling hold stable training at policy lag 64.

  4. Google Research72

    Google researchers detect hypertension signs with smartwatch PPG and accelerometer data, no cuff calibration needed

    Google Research published a Nature study on AI-PPG-ACC-HTN, a multimodal system that detects signs of hypertension from smartwatch PPG and accelerometer data without cuff calibration. Validated against 24-hour ambulatory blood pressure monitoring in 196 participants across five US sites, it reached 65.8% sensitivity and 90.0% specificity for initial screening, and 78.4% sensitivity and 90.9% specificity for confirmatory testing. The authors describe the work as early feasibility research, not a replacement for clinical arm cuffs or a standalone diagnosis.

    Why it matters: Google's cuffless smartwatch hypertension model is benchmarked against 24-hour ambulatory monitoring, showing how passive multi-day sensor aggregation could support opportunistic screening.

  5. Anthropic Research36

    Anthropic: Teaching AI to build scientific models

    Anthropic research argues that AI systems can now derive equations like the Hodgkin-Huxley model in an afternoon, but fitting experimental data is not the same as understanding. The work breaks scientific modeling into building, constraining, and interpreting models, and notes that AI has made the most progress on constraining them, where Bayesian inference is the standard method for mapping all plausible parameter sets rather than a single fit.

  6. Microsoft Research58

    Microsoft Research's PDD Kit formally verifies agent-written full-stack web apps

    Microsoft Research introduced PDD Kit, a research prototype that turns a developer's plain-language intent into a Verus formal specification, proves the coding agent's Rust code meets it for every input, and falls back to tests where a proof cannot reach. In a demo inside GitHub Next's Chopin, the team used PDD Kit to verify the login logic of Pet Store, a roughly 5,000-line Rust full-stack app, with the developer reviewing the intent artifact rather than the generated code line by line. PDD Kit only verifies Rust today, and its guarantees rest on six developer-approved trusted pieces, including the bcrypt password check and the two database lookups.

November 5Thursday
  1. Amazon Science18

    Amazon Scientist Hamed Karimi Wins 2026 ECML PKDD Test-of-Time Award

    Amazon senior applied scientist Hamed Karimi and coauthors Julie Nutini and Mark Schmidt received the 2026 ECML PKDD Test-of-Time Award for their 2016 paper on linear convergence of gradient and proximal-gradient methods under the Polyak–Łojasiewicz condition. The paper showed that this 1963 inequality guarantees linear convergence even when models lack a single best solution, unifying scattered optimization results and extending them to nonsmooth landscapes and algorithms such as coordinate, sign, and stochastic gradient descent. It has been cited over 2,000 times and appears in graduate textbooks.

  2. Zyphra Research36

    ZYFA: Fast and Accurate FP8 Attention Kernels on AMD MI355X

    Zyphra Research released ZYFA, BF16 and FP8 causal prefill attention kernels for AMD's MI355X (CDNA4, gfx950) supporting head dimension 128 and DeepSeek-V2's MLA shape. On activations from Mistral-7B, Qwen3-8B and DeepSeek-V2-Lite at 16K tokens, ZYFA's FP8 kernels reach 1.16–1.76× AITER's throughput, and on Gaussian inputs at 32K tokens 1.26–1.37× at head dimension 128 and 1.99× at the MLA shape. FP8 error is 62–78% lower than AITER's at head dimension 128.

  3. Apple Machine Learning Research38

    Apple's Learned Support Functions Speed Up RAG Retrieval

    Apple researchers presented "Amortizing Maximum Inner Product Search with Learned Support Functions" at ICML 2026, training small neural networks offline to route queries toward their best-matching keys faster. SupportNet learns the support function via input convex neural networks (ICNNs) to improve cluster routing, while KeyNet directly outputs the best-matching key vector, kept geometrically grounded by a consistency loss from Euler's theorem. Both are trained on the actual query distribution, trading an upfront amortization cost for faster, more accurate retrieval at inference time.

  4. Google Research47

    Google Research's Agile Deliberation helps humans define subjective AI categories

    Google Research introduced Agile Deliberation, a framework that turns subjective AI classifier creation into an iterative conversation where the AI helps users sharpen their own definitions. It splits the task into concept scoping and concept iteration, using vision-language models to surface borderline images and route feedback into an automatic prompt optimization loop. In 18 live 1.5-hour user sessions, the approach reduced user fatigue and anxiety and produced more consistent models that outperform standard baselines; the code is open-sourced on GitHub.

  5. Anthropic Research58

    Anthropic studies how researchers use Claude across scientific fields and tasks

    Anthropic analyzed 207,049 Claude and Claude Code research sessions from August 2 to September 30, 2026, using privacy-preserving classifiers, and found scientists use Claude most for data analysis and writing and least for data gathering and ideation. Data analysis accounts for 33.7% of Claude sessions and 48.1% of Claude Code sessions, against 27.6% of researcher time, while ideation takes 4.2% and 2.1% of sessions versus 7.1% of researcher time. The report estimates that wide adoption of current capabilities could roughly double research output in some fields, and full automation of non-physical work could lift fields such as computer science and statistics as much as 15-fold.

  6. Goodfire Research58

    Goodfire Research proposes mechanistic shaping to steer models via internal representations

    Goodfire Research proposes mechanistic shaping, a framework that adds penalties on a model's internal concept directions during training so it learns to rely on or express specific concepts rather than just maximize task reward. In chest X-ray experiments, an LLM agent used sparse autoencoder features to find tube-like shortcut directions, and reliance shaping beat both standard training and a balanced-data baseline.

November 4Wednesday
  1. Anthropic Research66

    Anthropic biology lab reports first prokaryotic vault particle structure, solved with Claude

    Anthropic's biology research lab reports the first 3D structure of a vault particle found in prokaryotic cells, a phage protein called L05 built from 96 copies with a mass of about 9.5 megadaltons. Under the team's direction, Claude searched a database of about 15 billion predicted proteins, designed DNA constructs, optimized a size-exclusion chromatography isolation that cut purification from three days to about 90 minutes, and ran RELION cryo-EM processing that produced a first full model in 34 hours. The preprint has been submitted to bioRxiv, and the team says the vaults' biological function remains unknown.

    Why it matters: Anthropic's biology lab reports the first 3D structure of a vault particle from prokaryotes, with Claude handling database search, construct design, purification and cryo-EM processing.

November 3Tuesday
  1. Ai2 · Allen Institute for AI55

    Ai2 releases StateBench to test how language models track state changes across long documents

    Ai2 introduced StateBench, a benchmark with four difficulty levels for long-context state tracking, from immutable assignment to self-referential and cross-referential updates. In tests, Gemini 3.8 Flash, Claude Opus 5.5, and GPT-6 Sol and Luna handled the easier levels but dropped to 13% or lower on the longest general finite problems, while 275M-parameter Gated DeltaNet and hybrid models trained from scratch generalized almost perfectly on the first three levels and transformers never learned the hardest one.

  2. OpenAI Alignment Blog58

    OpenAI examines eval-production behavior gaps in agent safety and the role of eval-awareness

    OpenAI researchers measured an eval-production behavior gap in agent safety: across six served models, success on the Respecting Warnings evaluation was 10.2 to 37.4 percentage points lower than on matched Codex production decisions, with the largest gaps in GPT-5.6 Sol and GPT-6 Sol. General eval-awareness alone showed weak association with the gap (R² = 0.008), while specific eval-objective awareness was stronger (R² = 0.370), and models most often verbalizing the wrong objective (resisting prompt injection) had the biggest gaps. In an intervention on GPT-6.1 Sol, a generic evaluation cue left success nearly unchanged (63.1% vs 63.4%), the correct objective cue raised it to 91.6%, and the incorrect objective cue cut it to 17.6%.

  3. Apple Machine Learning Research32

    Attention to Mamba: A Recipe for Cross-Architecture Distillation

    Apple researchers propose a two-stage recipe for distilling a Transformer into a pure Mamba architecture without any Attention blocks. The method first distills a pretrained Transformer into a linearized Attention model via an adapted kernel trick, then distills that into an adapted Mamba model. The resulting distilled Mamba retains most of Pythia-1B's performance, reaching 14.01 perplexity versus the teacher's 13.86, with some gaps on tasks relying on in-context recall.

  4. OpenAI Alignment Blog60

    OpenAI details training activation classifiers for safety and alignment

    OpenAI describes training activation classifiers, or probes, that read a model's internal residual stream activations to flag misaligned or policy-violating assistant completions, and says it has deployed them on internal and external traffic of its most capable models starting from GPT-5.6. The probes use an Attention probe architecture with MLP plus QV-attention and an exponential moving average, are trained on up to 1M messages labeled by reasoning-model judges, and run in streaming fashion on the inference engine so a completion can be blocked mid-turn. OpenAI reports excellent probe transfer across many post-training stages but more limited transfer across pre-training checkpoints, and says probes were overall more robust to jailbreaks than content-based classifiers in its red-teaming.

    Why it matters: OpenAI details how activation probes on internal model activations serve as a streaming safety layer, including their limits on transfer across checkpoints and retraining needs.

November 2Monday
  1. Zyphra Research58

    Zyphra introduces ZHA hierarchical attention, a sparse method with subquadratic routing

    Zyphra introduced Zyphra Hierarchical Attention (ZHA), a sparse attention method that builds a tree of compressed KV-cache summaries and routes queries top-down through it, giving subquadratic complexity with suitable top-p thresholds. Existing pretrained models can be adapted via a short KL-distillation phase using only a few billion tokens; on Qwen3.6-35B-A3B, ZHA adds 81,920 trainable parameters, about 0.00024% of the base model. On RULER-13 at 256K tokens the wide-tree model scored 96.2% versus 96.0% for dense attention, and the deep six-level tree scored 63.4% on LongBench v2 versus 58.0% for dense while attending to about 1.1% of the KV cache; a GPU roofline model projects 32-35x speedup over dense attention at 10M tokens.

  2. Anthropic Research70

    Anthropic releases FlashProve, an open-source zkSNARK system for provable LLM inference

    Anthropic released FlashProve, an open-source prototype that uses zkSNARKs to prove a response came from a committed model without revealing its weights. On Llama 4 Maverick (400B-parameter MoE, 4-bit weights), a single H100 generates proofs at about 110 tokens/second with ~19 MB proofs per 1,024-token request, roughly 70-95x the GPU time vLLM needs for the same work. The release includes executable prover and verifier code, a C++ fast verifier, a Lean verifier with machine-checked completeness, soundness and zero-knowledge statements, and a technical report, all under Apache 2.0.

    Why it matters: Anthropic's FlashProve shows zkSNARK-based proofs of inference are becoming practical for a 400B-parameter MoE model, with open code and Lean-checked security claims.

October 30Friday
  1. Microsoft Research40

    Microsoft builds synthetic enterprise data platform to evaluate Copilot

    Microsoft's Industry Evaluation Data Generation Platform creates full-scale synthetic enterprise environments to evaluate Microsoft Copilot without using customer data. Grounded in public sources such as O*NET occupational data, job postings, and SEC filings, it generates realistic tenants with users, meetings, emails, and documents, plus automated query pipelines and quality frameworks. Microsoft says this establishes the first standardized evaluation baseline for Copilot.