Find

Search

16,014results

Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation

In this paper, we present 1020 Group's submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality score prediction and the detection of error-free segments. Pterodactyl is a highly customizable, ultra-low cost system optimized for binary classification in translation triage and data curation. It is based on an LLM-as-a-judge approach, with prompt engineering and model selection guided by ROC analysis. We also developed several variants of Pterodactyl that were specifically adapted for subtasks 3.

Hacker News (AI)2 days ago

How do you keep up quality when you vibe-code?

▲ 5

arXiv AI Papers2 days ago

FERN: Cross-Benchmark Table Retrieval for Text-to-SQL with Frozen Retrievers and Learned Ranking

Text-to-SQL systems over large pooled catalogs must first retrieve the tables a question needs. We compare against the published table recall of RASL, which uses Claude 3.5 models to extract keywords and select tables, on pooled BIRD, Spider, and Fiben catalogs. FERN (Feature-Engineered Ranking with No generative LLM) instead fuses three frozen retrievers into 100 candidates, describes each with up to 120 features, and reorders them with LightGBM rankers fitted once on BIRD's training questions. On Spider, where it was not fitted, its candidate pool alone reaches RASL's published recall at fifteen tables (98.0), and the ranker raises the share of questions with every gold table in the top five (complete@5) from 83.9% to 95.6%. At five tables, FERN's recall is within one point of RASL's on Spider (96.7 vs 97.0) and on BIRD with its evidence hints (96.6 vs 97.5), and 8.2 points below on BIRD without them (89.3). On 121 real BEAVER questions, without BEAVER fitting, its recall at fifteen (82.1) falls between two BEAVER-trained retrievers (80.8, 84.5), but its complete@15 is below both (49.6 vs 54.5 and 62.0). On Fiben, it falls far short at fifteen tables (54.2 vs 69.2, different question sets), although its recall at fifty is numerically close to RASL's question-only retrieval result (80.7 vs 79.4). On BIRD dev with evidence, non-retrieval features raise complete@5 by 7.7 points over retrieval signals alone. On BIRD dev, median latency is 208 ms per question on one A100, without hosted model calls.

Hacker News (AI)2 days ago

Show HN: TheoremSmith: Mass-Producing Hard Proof Problems to Train LLMs

▲ 5

arXiv AI Papers2 days ago

C^2-Routing: Complementary Cropping and Compression for Efficient Vision-Language Inference

Visual Question Answering (VQA) imposes substantial computational overhead on vision-language models (VLMs), motivating model-agnostic input reduction methods that can be readily applied across diverse VLMs, including in black-box settings. Simply enforcing a visual-token cap reduces computation, but it can discard information needed to answer the question. A single reduction strategy also struggles to accommodate different scenarios. Our key observation is that cropping and compression are complementary: cropping highlights small targets and local details, whereas whole-image compression better preserves context for large targets or distributed evidence. Based on this observation, we propose C^2-Routing, which adaptively selects cropping or compression according to the input image and question. Since both strategies may still discard key information, we further design a safety gate that uses the predicted joint correctness distribution under original and reduced inputs to guide fallback and protect accuracy. To accommodate consumer GPU resource constraints, all training and evaluation experiments run on RTX 3090 GPUs. To measure gains beyond token capping, we use full-image baselines with the same cap of 1,024 visual tokens. We conduct extensive evaluation on three VLMs and 18 datasets spanning local details, global scenes, scene text, and documents. With the visual budget already capped, C^2-Routing further reduces end-to-end FLOPs by 36.53% and visual tokens by 42.36% on average, with a mean relative task-score decrease of only 0.77%.

arXiv AI Papers2 days ago

Bayesian inverse problems and epidemic-threshold uncertainty for a heterogeneous SIS reaction-diffusion model

We study Bayesian inference of persistence from early observations of a heterogeneous susceptible--infected--susceptible (SIS) reaction--diffusion model with standard incidence. We show that the leading prevalence dynamics depend on the unknown coefficients only through the difference between the transmission and recovery rates and the infected diffusivity. The same pair determines the principal eigenvalue whose sign governs persistence, so early prevalence can inform the threshold even when the individual rates remain uncertain. We prove global weak well-posedness and quantitative parameter stability for the SIS system and use the resulting observation-map estimates to establish Bayesian well-posedness. For an initial infection of size , we derive a uniform second-order expansion that describes how the separate rates enter prevalence. Incidence depends explicitly on transmission at leading order. When the noise standard deviation is proportional to , we prove O() convergence in Hellinger distance of the nonlinear posteriors to their low-prevalence limits for both prevalence alone and joint prevalence and incidence data. We bound the principal eigenvalue using the growth rate of the infected L^2 norm between two times. This rate gives a lower bound for the full nonlinear system, and the upper bound separates spatial transients from nonlinear saturation. Uniform spectral estimates and bounds on infection size and measurement error give sufficient conditions for persistence and extinction. We also bound the error in posterior persistence probabilities under forward and eigenvalue approximation, accounting for posterior mass near the threshold. Numerical examples illustrate threshold inference and the predicted (O()) convergence of the nonlinear posteriors to their low-prevalence limits in Hellinger distance.

arXiv AI Papers2 days ago

A Theory of Policy Optimization in Post-Training: Coverage Collapse and Reference Resets

Policy optimization is central to language model post-training, yet principled guidance remains limited. We revisit its theoretical foundations to identify algorithms that learn near-optimal policies using total samples and gradient steps governed by the base model's response coverage, a measure of how readily it generates optimal responses. We call such algorithms coverage-preserving. This guarantee captures the goal of amplifying capabilities accessible through sampling from the base model. (1) Coverage collapse. REINFORCE, the basis for PPO and GRPO, can drive the probability of optimal responses to near zero, even as reward improves. This coverage collapse stalls optimization, and convergence can require exponentially many steps despite good initial coverage. The failure arises even with exact gradients and persists under KL regularization to the base model. (2) Reference resets. We show that repeatedly resetting the KL reference to the most recent policy mitigates coverage collapse. We formalize this intervention in Approximate Policy Mirror Descent (APMD), a meta-algorithm that approximately solves a sequence of KL-regularized RL subproblems. APMD enables stronger regularization, making each subproblem easier to solve, while reference resets allow convergence to global optimality. (3) Coverage-preserving algorithms. For softmax linear policies over pretrained features, we use APMD to establish the first global convergence guarantees showing that widely used families of post-training algorithms are coverage-preserving. These include stylized PPO and GRPO variants with explicit KL regularization and reference resets, and squared-loss algorithms that implement them implicitly, including those used to train the Kimi models. These results clarify how regularization, clipping, and objective choice affect the sampling and optimization costs of post-training.

Hacker News (AI)2 days ago

Gemini 4 Carbon now available

▲ 5

arXiv AI Papers2 days ago

A Theory of Cross-Validation Variance

Cross-validation estimates predictive performance by repeatedly splitting the data into training and validation sets, fitting the model on the first and evaluating it on the second. Every observation influences the estimate in two roles, through its own evaluation when it is held out and through the models it helps fit when it trains. The random splits determine its weight in each role. From this representation, we prove an exact finite-sample identity for the variance of the cross-validated estimate. For a given splitting scheme with a common training set size, the variance is a function of these weights, with constants of the model, the metric, and the population. It covers metrics averaged over observations, such as mean squared error, and over case--control pairs, such as the AUC. The identity shows which schemes to use. The variance decomposes into sampling variance, which depends only on the training size, and variance due to the random fold splitting, which arises when the weights change from one draw of the splits to the next. K-fold cross-validation, whose weights are equal across observations by design, is therefore variance optimal at first order; Monte Carlo and bootstrap cross-validation are not. The first-order variance of K-fold does not depend on K, and under reasonable conditions on the model leave-one-out has the smallest variance of any K-fold scheme. For the AUC the same holds for leave-pair-out, which evaluates every case--control pair. Finally, we show the cross-validated estimate is asymptotically normal with the identity's full variance. Together, these results provide a general theoretical foundation for inference on cross-validated performance and establish principles for selecting variance-optimal cross-validation designs.

arXiv AI Papers2 days ago

Accurate predictions of properties of energetic materials with tabular foundation models

We use TabPFN, a recently developed tabular foundation model, to predict three properties of energetic materials: impact sensitivity, decomposition temperature and crystal density. Without any hyperparameter tuning, TabPFN outperforms the best published models for all three properties. It also substantially outperforms a wide range of established machine-learning models, including tuned gradient boosting (XGBoost), random forests and Gaussian processes. This holds both when the models are given hand-crafted molecular descriptors and when they are given learned representations from Chemprop's message-passing neural network. In particular, for all three properties, TabPFN applied to Chemprop's own embedding is more accurate than Chemprop's predictions. TabPFN is also among the fastest models we consider, more than an order of magnitude faster than XGBoost. As TabPFN predicts the entire distribution of the target rather than just a single value, it offers built-in uncertainty quantification, which we compare with the empirical distributions of compounds with repeated measurements. Finally, we interpret the predictions using Shapley values, which rank the features by their importance.

arXiv AI Papers2 days ago

When does text encoding matter for language modeling?

UTF-8's role as the de facto encoding standard in language models introduces cross-lingual inequities due to its variable-length design. However, the effect that this encoding choice has on model performance remains largely unexamined. In this work, we investigate how text encoding impacts the performance of byte-level language models, comparing UTF-8 with a wide range of other encoding strategies, including other Unicode-based approaches, language-specific encodings, and our own customized encodings. To facilitate our analysis, we propose Aether: a hybrid encoding scheme that uses script-specific encodings for our target setting while maintaining full Unicode coverage through UTF-8 fallbacks, using this framework to model four orthographically diverse languages. Surprisingly, we find that while languages with information-dense characters (Chinese, Korean) significantly benefit from compressive encodings, languages whose characters carry less information individually (Georgian, Tamil) are largely insensitive to encoding choice. In light of these findings, we argue that text encoding should be a language-specific design decision, rather than a universal default.

arXiv AI Papers2 days ago

UGG: Unified Generative Geometry Model

Understanding 4D scenes is a core challenge in visual intelligence, requiring models to jointly capture scene geometry, appearance, and dynamics from partial observations. However, existing approaches are subdivided into feedforward models for direct geometric prediction, and generative models for visual synthesis. We introduce UGG, a unified framework for 4D scene understanding that jointly models RGB video and geometric representations such as depth and camera pose. By assigning different noise levels across modalities and time, UGG formulates visual generation and geometric prediction as conditional completion within a single generative model. This flexible formulation enables the model to learn from diverse, heterogeneous datasets with different subsets of geometric and visual annotations. Furthermore, our generative formulation enables inference-time search over multiple plausible scene hypotheses, using geometric evidence extracted from observed RGB frames to improve geometric prediction without ground truth geometry. We demonstrate UGG's effectiveness over non-unified baselines across camera-controlled video generation, depth estimation, and camera pose prediction, including in challenging sparse observation settings. Code and visualizations are available at https://ugg-model.github.io/

AWS Machine Learning Blog2 days ago

Autonomous treasury agents: How Trovata built an AI-native solution on Amazon Bedrock and AgentCore

Learn how Trovata built autonomous treasury agents on Amazon Bedrock and Amazon Bedrock AgentCore, using an RBAC-secured architecture for bank-branded AI deployment and agentic workflows that move corporate treasury from manual operations to real-time decision-making at enterprise scale.

Hacker News (AI)2 days ago

Businesses in ChatGPT – OpenAI

▲ 5

Hacker News (AI)2 days ago

GPT-6.2 Sol: My Impressions/Review

▲ 5

arXiv AI Papers2 days ago

One Policy for 100 Household Tasks: Our Solution for the 2026 BEHAVIOR Challenge

We describe our solution for the 2026 BEHAVIOR Challenge: 100 long-horizon household tasks in the OmniGibson simulator. We placed 9th on the final leaderboard, the only independent team in the top 10. The core of the solution is a single vision-language-action (VLA) model, one checkpoint for all 100 tasks, built on our 1st-place 2025 solution, which is based on π_{0.5}. On the 50 tasks shared with 2025, its Q rises from 0.260 to 0.371; across all 100 tasks it scores 0.392. Our main conclusion from 2025 was that the model was undertrained, so most of the 2026 work went into training the model for longer, optimizing some training parameters, making each training step slightly faster and reducing the gradient noise: a migration from 50 to 100 tasks (semantic stages built from the demonstrations' skill annotations, task and stage embeddings of new tasks warm-started from similar old ones, and a 21-dimensional action space matching the teleoperation controls); variance-reduced multi-sample flow matching with a simple noise-vs-compute model that picks the number of action-expert samples per observation without ablations; and a 200k-step training run, about one pass over the 211M frames of the demonstrations. A cloud evaluation infrastructure keeps a shared record with provenance, episode diagnostics and restorable simulator states, and runs six simulators on one GPU together faster than real time. On top of the learned policy, 14 tasks are routed to a GPT-6 Astra coding agent that controls the robot through observation and motion tools, starting every episode from a frozen copy of its own practice session on training instances. Across these 14 tasks, Astra's mean Q is 0.639, against 0.108 for the learned policy. The public submission included only part of the Astra results and scored 0.446 Q with 27.3% full-task success.

arXiv AI Papers2 days ago

Two Communities, One Problem: Branch-and-Bound vs. A* for Resource-Constrained Project Scheduling

Branch-and-Bound (B&B) and A^* are popular exact search methods originating from Operations Research and Artificial Intelligence, respectively. Although the two methods share fundamental search principles, their different ways of exploring the search space can lead to substantially different computational performance. We investigate these differences using the Resource-Constrained Project Scheduling Problem (RCPSP) as an exemplary problem setting. We first establish the relationships between mixed-integer linear programming, state-action, and timed Petri-net representations. Since B&B and A^* admit numerous algorithmic enhancements, we focus on relatively basic implementations. This allows us to examine the fundamental differences between the methods rather than compare the performance of state-of-the-art solvers. By using the same lower bound and best-first node selection, we isolate the effects of the search mechanisms, particularly the identification of equivalent states reached through different scheduling decision sequences. Experiments on 480 benchmark RCPSP instances show that graph-based A^* substantially outperforms the B&B variants considered. With additional pruning rules, A^* proves optimality for all 480 instances, compared with 445 for best-first B&B under the same time and memory limits. Depth-first B&B uses less memory and can find feasible solutions even when the search does not finish within the time limit. Stronger linear programming relaxations reduce the search space but introduce considerable computational overhead. Our findings highlight the importance of duplicate-state detection and clarify the computational trade-offs between the search approaches. These insights can help researchers select an appropriate method and identify opportunities to incorporate effective mechanisms from one approach into the other.

Hacker News (AI)2 days ago

Work at the Frontier: AI's effect on freelance work

▲ 5

arXiv AI Papers2 days ago

Quantifying the Sampling Frequency Invariance of Time-Series Foundation Models for Sensor Data Applications

Time-Series Foundation Models (TSFMs) are increasingly used in sensor applications, where sampling frequency (SF) varies across sensors, devices, and operating modes (e.g., power saving). Ideally, TSFMs must remain effective during such SF changes, provided the SF retains task-critical bandwidth. In this paper, we stress-test 4 prominent TSFMs: MOMENT, Chronos-2, Moirai-MoE, and TimesFM, to quantify their SF-invariance and investigate whether their behavior tracks the resulting loss of information bandwidth rather than the SF value itself. Our stress-test probes 3 dimensions: (i) the shift in embeddings, (ii) the degradation in forecasting performance, and (iii) the degradation in downstream performance, quantified by three novel metrics: FSI, FDI, and CDI, respectively. To our knowledge, this is the first study to place SF-invariance at the core of TSFM evaluations. Our results characterize: (i) how SF-invariance depends on the margin between signal's native-SF and the bandwidth its task requires, (ii) how much of that invariance the choice of TSFM explains, and (iii) how much of TSFM's performance degradation under a lower SF reflects information loss rather than a limitation of their abilities. These findings reframe SF-invariance as a measurable, signal-aware property of the (signal X TSFM) pair, and guide practitioners on when TSFMs display SF-invariance.

Hacker News (AI)2 days ago

Show HN: Get your coding agent off ~2019 JavaScript, onto modern web primitives

▲ 5

arXiv AI Papers2 days ago