TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI

Open problems across fields

  • General in-context learning for embodied agents1 paper raises it · 0 address it

    Improving adaptability of models to new tasks and environments without task-specific fine-tuning is critical for scalable embodied intelligence.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Cost and latency in agentic systems2 papers raise it · 1 addresses it

    High computational and time costs limit practical deployment of agentic systems for real-world tasks.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
    • PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviewsraises · addresses
  • Physical-state verification and failure recovery1 paper raises it · 0 address it

    Robustness to irreversible failures and accurate state tracking are essential for reliable embodied control.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Evidence-grounded multimodal reasoning benchmarks1 paper raises it · 1 addresses it

    Current benchmarks often fail to ensure models use necessary audio-visual evidence, weakening evaluation reliability.

    • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses
  • Length generalization in sequential state tracking1 paper raises it · 1 addresses it

    Models struggle to maintain performance on problems much longer than their training data, limiting scalability.

    • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses

Named by an AI from these papers' abstracts.

Fields · this week
All fields3517Multimodal573Agents540Frontier LLMs478Inference & serving282Image segmentation198Graph learning178Learning verifiable rewards1673D scene166Voice AI101Forecasting time88Classifier & causal discovery88Flow matching76Evals60Teacher policy distillation55Adversarial training53All 32 fields

Papers

  • arXiv cs.CROct 16

    Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction

    Mohamed Shaaban, Mohamed Elmahallawy, Thomas E. Carroll

    Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts containing personally identifiable information (PII) to remote providers exposes data subjects and organizations to risks from logging, retention, model training, and unintended disclosure. Existing anonymization methods often mask or remove PII, while conventional encryption eliminates the lexical and structural cues needed for effective LLM processing. We present Veil-then-Reveal (VtR), a user-side PII pseudo-anonymization framework for privacy-preserving LLM interaction under a zero-trust threat model. VtR treats remote LLM providers as untrusted and sends only pseudo-anonymized prompts, keeping plaintext PII on the user. VtR first detects PII and replaces it with realistic, same-type, in-vocabulary surrogates before prompts leave the user's device, preserving their linguistic and structural properties. It combines format-preserving encryption (FPE) for structured PII, such as phone and credit-card numbers, with a keyed-hash dictionary and secure vault for semantic PII, such as names, locations, and organizations. Session-specific mappings provide cross-session…

    PDF
  • arXiv cs.IROct 16

    Reasoning Reranking with Semantic IDs as the Sole Item Representation

    Zhenwei Tang, Jintao Liu, Di Bai, Xidong Wu, Xinwu Cheng

    Reasoning rerankers write a rationale before ranking a candidate slate, and existing systems read item metadata to do so, even though generative recommenders increasingly represent items as compact Semantic IDs (SIDs). Ranking from SIDs alone has two appeals: SID prompts are far shorter than the matched item text, and although item codes are fixed from content, the backbone learns their token embeddings in part from user-item interaction sequences, so the tokens can carry behavioral signal that item text lacks. That training targets next-item generation, and whether it supports ranking a supplied slate from SIDs alone is untested. We build ReRankID, a controlled testbed in which models reason and rank from a history and slate shown only as SIDs, varying item rendering, history length, and slate size one at a time. On this testbed, such models often copy the input order instead of reranking, and readable metadata does not repair the failure. We compare supervised fine-tuning, rejection-sampled self-training, on-policy distillation, and verifier-based reinforcement learning as post-training methods and find that they elicit the missing behavior. The strongest post-trained model,…

    PDF
  • arXiv cs.CLOct 16

    Causal Latent Workspaces for Looped Transformers

    Ilia Zaznov

    Reusing a Transformer block across depth increases computation without replicating its parameters, but successive passes have no dedicated state through which positions can exchange compact summaries of their causal prefix. We introduce the causal latent workspace Transformer: an anchored, four-round shared-depth architecture in which each position writes gated vectors into prefix-specific latent slots and retrieves a content-addressed summary before the next shared block application. This path complements causal self-attention while the original input embedding remains accessible at every round. Across three byte-level corpora, three seeds, and two matched parameter budgets, the proposed model achieves the best mean held-out perplexity in five of six settings against five Transformer controls. At 101.71M parameters it leads on WikiText-103 raw, enwik8, and TinyStories, reaching perplexities 2.7820, 2.7843, and 1.6823; these improve upon the strongest non-workspace control on each corpus by 1.06%, 0.73%, and 1.01%. All nine seed-labelled comparisons at this budget favor the workspace. At 0.918M parameters it leads on WikiText-103 and TinyStories, whereas a conditioned loop is…

    PDF
  • arXiv astro-ph.IMOct 16

    Analysis of Binary O-type Star Systems Using Recurrent Neural Networks

    Miguel Flores R., Luis J. Corral, Celia R. Fierro-Santillán, Silvana G. Navarro

    This work presents an initial analysis of the estimation of effective temperature and surface gravity for simulated O-type binary systems using a recurrent neural network. The proposed system uses 34 equivalent-width measurements from the optical region of a stellar spectrum. Two methods were applied to observed IACOB spectra before normalization: the addition of a blackbody continuum and the addition of a second observed spectrum. The first method produces only small differences in the normalized line profiles and in the estimated physical parameters over 3700-7000~Å. In the second method, the secondary spectrum is added with contributions of 5, 10, 20, 30, 50, and 75 per cent, as defined relative to the original primary spectrum. The general comparison includes 192 simulated systems and 1152 modified spectra. For most of these spectra, the estimated effective temperature and surface gravity decrease as the contribution of the secondary component increases. Individual examples using HD14947, HD190429, HD48099, and HD206267 show that this behavior is not the same for every combination: some estimated effective temperatures fall below the estimates for both isolated spectra, and…

    PDF
  • arXiv cs.CVOct 16

    STRIDE: Evaluating Spatiotemporal Reasoning in Driving Edge Cases

    Lieqi Liu, Rui gao, Jia-Chen Gu, Wenbo Hu, Zhaobin Mo +4

    In autonomous driving, perceiving surrounding objects is not enough: failing to understand how they move and interact over time can lead to dangerous decisions. Evaluating vision-language models (VLMs) therefore requires testing whether they connect past spatial observations to future consequences. Yet existing benchmarks often assess edge cases through basic perception questions or test temporal understanding in simple scenarios, leaving complex spatiotemporal reasoning underexplored. We introduce STRIDE (SpatioTemporal Reasoning In Driving Edge Cases), an object-centric benchmark for long-tail, safety-critical driving scenarios. STRIDE covers six task families: spatial perception, spatial understanding, temporal memory, temporal extrapolation, trajectory prediction, and scene-context awareness. It pairs multiple-choice questions probing individual spatiotemporal judgments with related free-form visual question answering (VQA) requiring detailed scene explanations and justifications of driving decisions. We prioritize scenes with unusual object behaviors and complex traffic interactions, generate reference answers from structured dataset annotations through automated procedures,…

    PDF
  • arXiv cs.LGOct 16

    Ori: Drift-Aware Streaming $k$-PCA for Very Low-Rank LLM Training

    Xinyu Luo, Jincheng Zhou, Mengbo Wang, Zilin Shen, Nadia Atallah Lanman +3

    A prominent family of low-rank LLM optimizers, pioneered by GaLore, performs gradient-subspace projection: at each step, they project the gradient into a low-dimensional subspace and map the update back to the full model. Most existing work either recomputes the gradient subspace at certain intervals, or performs post-hoc adaptation to catch up to the moving subspace. In this work, we explicitly identify in practice the slow, stable manner in which LLM gradient subspaces drift across time. To this end, we propose Ori, a novel low-rank optimizer for training LLMs that captures the shifting principal gradient directions over time to achieve state-of-the-art accuracy under stringent low-rank constraints. Ori employs a streaming $k$-PCA algorithm inspired by Oja++, whose low per-step cost enables high-frequency, on-the-fly subspace tracking. In practice, Ori reduces the performance gap of the state-of-the-art low-rank optimizers to full-rank optimizers by up to 69.3\% on a 1B LLaMA pretraining task, and achieves the best performance on 10 out of 16 task scenarios in Roberta-Base fine-tuning. Together, these contributions allow Ori to further push the performance and efficiency…

    PDF
  • arXiv cs.CLOct 16

    Prune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning

    Mohamed Shaaban, Mohamed Elmahallawy

    Fine-tuning large language models (LLMs) on proprietary records enables domain adaptation but introduces two challenges: (i) privacy leakage of memorized private data, such as personally identifiable information (PII), and (ii) balancing private data removal with utility preservation. Existing defenses, including data sanitization and differential privacy, often degrade performance, while privacy-neuron editing lacks a PII-free reference to distinguish identity-specific neurons from those supporting useful text. We propose JEPA-Prune, a post-hoc neuron pruning framework guided by a model trained exclusively on PII-free views. Alongside the fine-tuned private model, JEPA-Prune, trains a public model on surrogate and masked views of the same records using a joint-embedding predictive architecture (JEPA), capturing domain knowledge without identifiers. A cross-model representation probe quantifies deviations between private representations of leaked records and this PII-free reference. Integrated gradients and a scale-invariant specificity score then identify PII-responsive neurons, which are pruned without retraining. Experiments show that pruning just 1.6% of neurons reduces PII…

    PDF
  • arXiv cs.CLOct 16▲ 46

    Self-Evolving Coding Agents via Harness-Policy Optimization

    Zhepei Wei, Wenlin Yao, Baolin Peng, Danqing Wang, Qianhui Wu +3

    Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the harness that mediates their interaction with the environment. Indeed, harness and policy are mutually reinforcing and evolving only one component is suboptimal---a harness tuned for one checkpoint may not target the failure modes of an updated policy, while policy learning remains limited to the trajectories elicited by a fixed harness. In light of this, we propose Self-HPO, a recursive self-improving framework for coding agents that alternates harness and policy optimization, using the evolving policy as its own harness proposer. Specifically, in each round, the current policy first analyzes its own failures and proposes new harness candidates (H-step). The policy is then updated through reinforcement learning (RL) under the selected harness (P-step), and hard tasks identified during training form the next harness search set, keeping harness optimization targeted to the policy's evolving failure modes. Across three coding benchmarks, Self-HPO consistently outperforms harness-only and policy-only baselines, improving…

    Code
  • arXiv cs.LGOct 16

    Next Token or Vector? Learning How Far to Decode

    Sai Sreenivas Chintha, Chidera Biringa, Rishab Sharma, Anusha Agrawal, Prachi Badarayani +4

    Standard autoregressive decoding advances one token at a time, even when several upcoming tokens can be predicted together. We propose CADENCE (Context-Adaptive DEcoding), a generation method that learns both what to draft and how far to draft. Gaussian prediction heads represent future spans as continuous latent vectors, and a shared decoder converts the selected vector into token predictions in parallel. A learned router selects the prediction length from the model's own hidden states and predicted Gaussian parameters, adapting generation granularity to the current context with single-token generation as a fallback. The backbone verifies each proposed continuation and retains the prefix that matches its greedy predictions. Experiments with Llama-3.1-8B-Instruct on Alpaca, GSM8K, and HumanEval show that router-selected positions yield higher draft acceptance than applying the corresponding prediction length everywhere. CADENCE achieves up to 1.3x higher generation throughput than standard greedy decoding.

    PDF
  • arXiv cs.GTOct 16

    Anytime Contracts for AI Services

    Boris Velasevic, Eden Saig, Eric Mazumdar

    AI services are prone to moral hazard, as model providers can silently route requests to cheaper, lower-quality models, and the inherent stochasticity of model outputs makes this degradation hard to detect. Contract theory addresses moral hazard by designing payment rules that reward high-quality outputs and prevent strategic overcharging. However, existing frameworks assume interactions of fixed duration, whereas AI services are typically consumed through subscriptions and pay-as-you-go APIs that users can terminate at any time based on observed performance. We show that this flexibility can break standard contracts, opening them up to abuse by either the providers or users. To address this, we extend contract theory to account for unknown exit rules. We formalize the problem as a Principal-Agent game, and show that budget-optimal contracts in this setting are proportional to anytime-valid hypothesis tests based on likelihood-ratio e-values. We give an efficient algorithm for computing anytime contracts and show how betting e-processes can be used to approximate them when the models are unknown. Finally, we evaluate our findings on synthetic data and data from deployed LLMs.

    PDF
  • arXiv cs.AIOct 16

    When Can You Trust an Agent's Own Verifier? Stress-Testing Counterfactual Rationale Verification Under Search Pressure and Oracle Access

    Jonghyun Lee, Moonsu Kim, Sunghwan Park

    Automated agent design increasingly trusts a single score to decide whether a change is an improvement -- but a score optimized aggressively enough ceases to measure what it was meant to. When an agent also explains its design, that explanation is a second signal we can check without human labels: negate each stated claim, re-run, and observe whether performance drops. We ask whether such a verifier stays reliable once an agent optimizes against it. Our contribution is not a new verifier but a way to stress-test one: a pressure ratio $ρ$ measuring how much the verifier steers the agent's search, and four falsifiable probes covering four failure modes -- giving no signal, being too weak to matter, being gamed by stating fewer claims, and being queried before the agent commits. We apply the test to our own verifier, the Rationale Consistency Score (RCS), inside an LLM agent that designs machine-learning pipelines, with one generator model, six tasks, and three seeds. First, in our prior configuration the verifier barely affects the search objective ($ρ\ll 1$), partly because of an accuracy gate, so its robustness had not been tested; it still shapes the reported artifact through a…

    PDF
  • arXiv cs.CVOct 16

    Direct Conditional Parameterization for N-Dimensional Splatting

    Zhongpai Gao, Benjamin Planche, Van Nguyen Nguyen, Meng Zheng, Anwesa Choudhuri +3

    N-dimensional splatting extends 3D Gaussian Splatting with view direction and time to model view-dependent and dynamic effects. Each primitive is lifted into a joint distribution over position and conditioning variables, then conditionally sliced at each rendering query. N-DGS and UBS share this step across Gaussian and Beta kernels: recovering the conditional mean, opacity, and covariance requires per-primitive matrix inversions and regression products in every forward pass. We introduce direct conditional parameterization, replacing this covariance-derived readout with explicit per-effect parameters: a Cholesky precision factor for opacity and a factorized query-to-position regression operator with learnable per-dimension coupling. Unrestricted conditional coordinates recover a valid joint covariance; our factorization adds spatial-scale and coupling priors. Applied to both kernels, the parameterization yields dGS (Gaussian) and dBS (Beta). Across five static and dynamic benchmarks, they match or exceed their covariance-derived counterparts on quality, with gains up to +1.26 dB in the main MCMC evaluation. Production slicing is 6.9-7.7 times faster than on-the-fly…

    PDF
  • arXiv cs.LGOct 16

    Reusing Calibration Gains across Model Representations

    Xu Cao, Wenxuan Xiao

    Scale calibration learns an update for one model representation. We study how much of that update can be reused by another representation of the same pretrained model. Our transfer procedure extracts positive group-wise gains and installs them in the recipient's weights or native quantization scales without recipient-side optimization. On a quantized recipient, it preserves integer codes, zero points and storage layout. For a Qwen3-1.7B floating-point/GPTQ INT3 pair, bidirectional transfer retains 76.9-90.5% of the text-loss improvement from recipient-specific calibration on fresh WikiText and C4 cohorts excluded from project development. Shuffling the same gain values within each projection worsens both recipients, showing that their learned group assignment matters after transfer. A Llama-3.2-3B control keeps the initial native tensors at all four calibrated projections identical and changes nine projections elsewhere. Cross-installation retains 98.6-99.3% of the text-calibration benefit, alongside a small, resolved preference for each recipient's own gain. These results quantify both the adaptation carried by a reusable calibration update and the remaining benefit of…

    PDF
  • arXiv stat.MLOct 16

    Unit-level aggregation breaks coverage in causal foundation models

    Gabe Schulman, Lucius E. J. Bynum, Yoav Wald

    Causal foundation models (CFMs) show promising results for treatment-effect estimation, with unit-level estimates that are competitive on standard benchmarks. Many causal analyses, however, inform decisions through effects averaged over groups of units, such as the full sample, the treated units, or a subgroup, and for such decisions a CFM is useful only if its credible intervals are calibrated. We examine these intervals and find that their coverage degrades, both in simple synthetic settings and on standard benchmarks. On ACIC 2016, for example, temperature-calibrated 95% intervals from CausalPFN fall below nominal coverage beyond groups of 30 out of 4802 units, and intervals for the full-sample average contain the true value in only 20% of datasets. We trace this problem to how these models are trained and how their intervals are formed. They output a predictive distribution for one unit at a time and, at inference time, combine the unit-level variances as if the errors on different units were independent. We show formally that posterior uncertainty over the data-generating process makes these errors correlated. As a result, the combined variance is too small by a factor that…

    PDF
  • arXiv cs.DCOct 16

    One Communicator, Three Vendors: Extending the MoA Predictive Theory to a Real NVIDIA+AMD+CPU MPI Ensemble

    Lenore Mullin, Gaetan Hains

    The companion MPI-extension paper validated the first communication-bearing machine-shape ensemble: four NVIDIA A100 ranks and four CPU ranks on one NCSA Delta node under one Open MPI job, reassembled by MPI_Gatherv. This paper extends it to a multi-vendor communicator. A Slurm heterogeneous job spanning Delta's A100 and AMD MI100 partitions places A100, MI100 and CPU ranks (nine in all) under one communicator for the first time. We give the theory (a w_i proportional to 1/t_i weight split for three concurrent realizations; a het-job specification as an admissible directive) and report real results, including what the run exposed: the 1/t split assumes time linear in rows, and this fails for the MI100 rank (6 rows took 597 ms against a linear prediction of 1.6 ms). A launch-geometry model, with predictions recorded before measuring, succeeds for the A100 (time flat from 128 to 3456 rows, stepping at exactly 3520 and 6976) and places the MI100 floor in the key loop; changing its launch settings cut about 600 ms to 14.6 ms and the energy per call at 6 rows by 32x, though the MI100 remains about 95x slower than an A100 at 8192 rows. Controlled reruns show that the companion paper's…

    PDF
  • arXiv cs.AIOct 16

    StoBasket: Joint Upsell and Cross-Sell Optimization for Contribution Margin

    Xin Heng

    Retail recommenders rank relevance, but retailers earn contribution margin: an upsell earns the margin difference over the item it replaces, whereas a cross-sell earns its full margin. We introduce joint stochastic basket editing, a formulation in which one policy selects replacement and addition offers for an existing basket, values them by expected incremental contribution margin, and couples them through displayed-offer, accepted-offer, and joint-acceptance response channels. To our knowledge, it is the first formulation in which upsell and cross-sell responses are coupled; prior separable treatments are its zero-coupling special case. In real-data-calibrated simulations on five public basket datasets, StoBasket captures essentially all attainable offer margin: within 0.5% in every default-price setting and within 0.7% when the true response lies outside its model family. Correct economic accounting is the broadest gain: margin-weighted popularity leaves up to 11% of attainable margin unrealized, and a published next-basket recommender leaves 11-52%. Joint selection adds 10.2% of attainable margin on Instacart, where premium tiers and add-ons are strongly linked. When offers…

    PDF
  • arXiv cs.LGOct 16

    Acquisition Function-Guided Generation for Bayesian Optimization over Discrete Spaces

    Tommaso Ancilli, Thomas Wedenig, Henry Moss, Robert Peharz

    Bayesian optimization (BO) over discrete spaces is challenging due to missing gradients and the sparsity of valid solutions. Latent-space BO sidesteps both issues by fitting a surrogate in the latent space of a generative model, which however substantially complicates the direct incorporation of domain knowledge that is naturally expressed in the original discrete space. In this work, we instead combine a pretrained generative model with a surrogate defined directly in data space, where inductive biases such as domain-specific kernels can be readily incorporated. Rather than maximizing the acquisition function over the discrete design space, our method samples candidates from the generative model under a distribution tilted by the acquisition function. To recover useful gradients for sampling, we embed this tilted distribution into a diffusion bridge that yields a smooth, posterior-averaged acquisition function. This leads to \emph{acquisition function guided generation} (AFGG), which we instantiate with a categorical diffusion model and an autoregressive normalizing flow. Across a broad suite of molecular benchmarks, the diffusion model variant performs on par with leading BO…

    PDF
  • arXiv cs.ROOct 16

    Shape-Aware Neural Time Fields for Rigid-Body Motion and Manipulation Planning

    Yanming Zhou, Yuchen Liu, Ahmed H. Qureshi

    Rigid-body motion planning is fundamental to robotic transport and manipulation, where both object position and orientation determine whether a body can move through cluttered environments. This coupling makes planning chal- lenging because translation and rotation can be constrained very differently by surrounding geometry. We propose Shape- Aware Neural Time Fields, a physics-informed neural motion planning framework that learns a reusable travel-time, or cost- to-go, representation for rigid-body motion while explicitly accounting for these distinct geometric restrictions. The learned field captures local motion difficulty in translation and rotation and is paired with a sampling-based planner that balances progress toward the goal with the cost of reaching nearby poses. We evaluate the framework across 2D and 3D rigid- body planning tasks and non-prehensile manipulation through object pushing in diverse environments. Results show substantial improvements in planning success and inference efficiency over physics-informed neural planning baselines, while remaining competitive with classical sampling-based planners at significantly lower planning times. Ablation studies further…

    PDF
  • arXiv cs.AIOct 16

    Between Spoilers and Guesswork: Avoiding Over-Specification in Coding Benchmarks

    Yuanzhe Liu, Bastian Lipka, Avraham Shinnar, Jatin Ganhotra, Yao Ma +1

    Benchmarks drive AI progress, but are hampered by task under-specification and over-specification. Task under-specification causes guesswork, where solutions have to make things up, or worse, resort to contamination or reward hacking. Task over-specification causes spoilers, where solutions can bypass some of the harder steps the benchmark was supposed to measure. Since future-looking benchmarks should be difficult, over-specification reduces a benchmark's shelflife of community adoption. Repository-level coding benchmarks have helped the field progress but experience unnecessary churn due to both over- and under-specification. For instance, SWE-bench Pro, FEA-bench, Doc2Feat-bench, and Multi-SWE-bench all tackle under-specification by augmenting task statements with hints derived from ground truth. We show that leaking ground-truth information into the task statement causes over-specification in some of these benchmarks. We experiment with various specification levels, trying to thread the needle between spoilers and guesswork. Based on these results, we recommend techniques for deriving parsimonious hints. We will release our hints so the community can obtain more reliable…

    PDF
  • arXiv cs.CVOct 15

    Input- and Feature-Space Correction for Cross-Hospital IHC Grading

    Jongwoon Lee, Jhair Gallardo, Christopher Kanan

    Pathology foundation models (FMs) are trained predominantly on hematoxylin and eosin (H&E) images but are increasingly used as frozen feature extractors for immunohistochemistry (IHC), where cross-hospital differences can impair grading. However, systematic comparisons of correction methods for cross-hospital IHC grading remain limited. To address this gap, we benchmark label-free transformations applied to input images before frozen-FM encoding and to features after frozen-FM encoding using UNI and Virchow2, three IHC markers, and six directed cross-hospital transfers, yielding 12 settings. Among the evaluated input-space methods, our proposed method FIX achieved the largest macro-F1 improvement over no correction, outperforming well-known stain normalization techniques. Among feature-space methods, a simple feature-wise standardization achieved the best improvement over no correction, outperforming CORAL. Under patient-averaged tile-level evaluation, combining FIX with feature-wise standardization improved macro-F1 and quadratic weighted kappa (QWK) by 0.181 and 0.208, respectively, and reduced ordinal error by 0.209 relative to no correction. These results show that input- and…

    PDF
Load more
PDF

Rising research topics

  • Training & fine-tuning42+90.9%
  • AI safety29+61.1%
  • Quantum machine learning28+33.3%
  • Computer vision29+31.8%
  • Federated learning51+27.5%
  • Evals60+25.0%
  • Code models13+18.2%
  • Forecasting time88+12.8%