Transformer Encoder

Transformer-based foundation models are powerful but opaque, motivating Mechanistic Interpretation methods to uncover the black-box by identifying small computation subgraphs responsible for a task. DiscoGP is a joint weight-and-edge circuit discovery framework originally developed for text decoders. We extend DiscoGP to speech encoders and present, to our knowledge, the first circuit discovery study for modern speech foundation models. Across HuBERT and Wav2Vec 2.0 on several speech classification tasks, we find that the discovered circuits are extremely compact, yet often match or even exceed the performance of the full pretrained encoder with the same downstream head. Through ablations, we show that these circuits reflect pretrained computation rather than random structure or task-head artifacts. We also introduce a memory-efficient DiscoGP variant that reduces the GPU memory cost of edge-circuit discovery at runtime from quartic to cubic. Overall, our results broaden Mechanistic Interpretation beyond text decoders and show that circuit-level analysis can reveal both explanatory structure and unexpected functional behavior in speech encoders.

Understanding why individuals respond differently to psilocybin requires modeling the drug's transcriptional perturbation signature at the cell-type level. I present a Transformer-based delta expression encoder that learns to classify differential gene expression status - upregulated, downregulated, or neutral - from single-nucleus RNA-sequencing data, without supervision from pathway annotations or prior biological knowledge. The model is trained on pseudobulk profiles from 623 examples spanning 18 cell types, 2 drug conditions, and 6 timepoints derived from the Liao et al. 2025 dataset, and achieves 69.4% weighted classification accuracy. Three principal findings are reported, alongside one direct test of a published hypothesis that returned a result inconsistent with that hypothesis. First, per-cell-type classification accuracy ranges from 28.3% (L2/3 IT, a primary HTR2A-expressing psilocybin target) to 99.6% (endothelial cells), consistent with known psilocybin response biology. Second, psilocybin-induced transcriptional downregulation is significantly more stereotyped across individuals than upregulation (Mann-Whitney U=18615.0, p<0.0001), a novel finding with a cortical depth gradient across excitatory subtypes. Third, attention-guided gene co-regulation analysis recovers drug-specific modules without pathway supervision. Separately, a direct test of whether baseline HTR2A expression predicts drug-response separability across cell types found a significant negative correlation (Spearman r = -0.7088, p = 0.0021), the opposite of what a simple HTR2A-gating account would predict.

Whisper exposes speech through a fixed 1500-token encoder interface, now a default representation for ASR decoders and Whisper-based speech language models (SpeechLMs), yet its redundancy remains largely unexamined. We propose stride-k subsampling, a deterministic indexing operation that retains every k-th token after the convolutional stem or encoder transformer. Across five Whisper scales, k=2 preserves baseline WER at both positions, with CKA attributing this stability to acoustic overlap at the stem and attention-induced redistribution at the encoder output. Applying stride-2 at both positions cuts audio tokens by 75% and total GFLOPs by 52-58%, with small WER costs on most ASR benchmarks and larger costs on harder ones. The same configuration extends to three Whisper-based SpeechLMs, yielding modest accuracy drops on stronger baselines and larger drops on weaker ones, while reducing end-to-end latency by 19.6-27.4%. Requiring no training or auxiliary computation, stride-k subsampling exploits Whisper's preprocessing redundancy, indicating that its audio-token interface carries more capacity than downstream tasks require.

Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling calibrated on the training distribution rather than on the scene at hand. Indoor scans vary widely in spatial extent and object count, so a fixed query set over-initializes small scenes and under-initializes large ones, while learned absolute and relative encodings are bound to the training scenes' extents and can saturate. We present AQ3D, which is designed to handle scenes of various sizes during training and inference. Queries are instantiated at a fixed ratio of the scene's superpoints, forming an overcomplete set whose background rejection is entirely left to the decoder. Positional information is encoded using 3D RoPE over quantized metric coordinates, replacing learned bounded lookup tables of prior decoders. Further, we improve the decoder itself by using attribution-based superpoint pooling, a mask refinement branch, and a cosine classifier for background rejection. Experiments show our method sets a new state-of-the-art on validation and hidden test splits across the datasets ScanNetV2, ScanNet200, and ScanNet++V2 among decoder methods trained without additional data augmentation. Code is available at \href{https://github.com/kenomo/aq3d}{github.com/kenomo/aq3d}.

Financial text is produced and interpreted within a market environment, yet financial text classifiers almost always receive text alone. We study whether financial time series are useful as an additional input on the task of classifying sentences from Federal Reserve communication as hawkish, dovish, or neutral. Our system, \lfts{}, extends the \lf{} architecture with this modality: a small voting network combines three independently trained components, a fine-tuned RoBERTa encoder, a prompted large language model (LLM), and a fused ensemble of time-series transformers over the market series of the months preceding publication. Because only about a thousand annotated sentences are available for training, the RoBERTa encoder is first pre-trained on sentences annotated automatically by the LLM and only then fine-tuned on the human labels. Trained on Federal Open Market Committee (FOMC) communication up to 2015 and evaluated on 2015--2022, the fused system achieves 70.2% weighted F1 -- against 64.1% for the zero-shot LLM -- and overtakes it with as few as 240 human-labelled sentences. We take this as initial evidence for market time series as an input modality in financial text classification.

The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert. This makes the VLM a context encoder rather than a decision-maker. We introduce G0.5, a pretrained autoregressive VLA in which a single transformer decoder emits reasoning and action tokens under a single objective. Three components make this tractable at foundation-model scale: a learnable cross-embodiment action tokenizer that maps heterogeneous robot actions into a shared vocabulary; a native chain-of-thought stream interleaving task decomposition, object grounding, and action hints with action tokens; and a visual memory module that injects multi-second history through the vision encoder. Because reasoning and action share a single set of weights, the pretrained VLM's capabilities carry over to physical behavior: the model follows instructions closely, and prompts directly steer action granularity, task horizon, and out-of-distribution scene handling without further training. Pretrained on a large collection of robot datasets together with VQA samples, G0.5 surpasses state-of-the-art models across 7 independent regimes: real-world fine-tuning on R1lite and R1pro robots (76.7% vs.\ 53.3% for $π_{0.5}$ and 24.4% for GR00T-N1.7), the 2025 BEHAVIOR Challenge on 50 long-horizon household mobile manipulation tasks using a generalist policy (31.4% vs.\ 26.3% for $π_{0.5}$ and 26.1% for the challenge winner), DROID post-training followed by zero-shot transfer to an unseen environment and objects (82.5%), a language-following Pick-and-Place benchmark, LIBERO (98.9%), RoboTwin 2.0 (93.3%), and SimplerEnv-Bridge (87.3%).

Sign language translation has achieved strong results with Transformer architectures, yet recent improvements largely rely on scaling model capacity at the cost of increased computation. We propose a parameter-efficient alternative that improves expressiveness without increasing model size. Rather than scaling capacity, we focus on enhancing the update dynamics of iterative refinement decoders, where each refinement step corresponds to one internal decoder iteration that progressively improves the latent representation before translation generation. We reinterpret residual refinement updates from an Ordinary Differential Equation (ODE) perspective and replace them with higher-order numerical integration schemes, namely Runge--Kutta methods (RK-2 and RK-4). These methods perform multiple function evaluations within each refinement step to produce more accurate and stable representation updates without adding decoder parameters. To the best of our knowledge, this is the first application of ODE-inspired update dynamics to sign language translation. RK-2 achieves 22.96 BLEU-4 on the PHOENIX-2014-T test set and 19.34 BLEU-4 on the CSL-Daily test set, outperforming the IPSLT baseline on both benchmarks, with fewer decoder layers and refinement iterations on CSL-Daily. These results suggest that stronger refinement dynamics can improve translation performance under parameter-efficient decoder designs, providing a complementary alternative to conventional model scaling.

Deep decoder-only Transformers often replace the original Post-Norm architecture with Pre-Norm variants because Post-Norm training is highly sensitive to warmup and learning rate under conventional initialization schemes. Although prior work has identified rank collapse and gradient vanishing as related symptoms, it remains poorly understood how causal attention creates high-similarity representations and why training dynamics fail to repair them. We give a two-stage analysis of Post-Norm rank collapse using token similarity as a scalar state variable. First, at initialization, causal attention acts approximately as a prefix-averaging operator that increases token similarity across depth, while the SwiGLU branch contributes only a smaller damping effect. Second, once training enters a high-similarity regime, growth of pre-normalization residual norms makes the RMSNorm backward factor contractive; under mild conditions, gradients to earlier layers decay geometrically. As a complementary result, we characterize the properties of a collapsed network: its best predictor is frequency distribution with relatively high loss floor, and gradients in collapsed layers vanish at frequency distribution. Experiments on 48-layer decoder-only Transformers trained on C4 dataset match the predicted initialization-time similarity growth and collapse-time gradient contraction, and show that collapsed runs stay near the predicted frequency loss. Together, these results distinguish the forward similarity amplification and backward repair incapacity in Post-Norm collapse, while also characterizing the behavior of collapsed networks.

This work investigates whether Electroencephalograph (EEG) foundation models (EFMs) can be made faster and locally deployable without sacrificing accuracy. EEG foundation models are a major trend, offering strong general-purpose representations. However, their computational burden grows quadratically with input length, hindering deployment on resource-constrained scenario, particularly for real-time clinical monitoring. EEG's low SNR further suggests many of these tokens are redundant and compressible with little accuracy cost. We propose ZIPBrain, a novel redundancy-aware EEG token pooling module that leverages this low-SNR characteristic to reduce token count. Given a token sequence, ZIPBrain partitions tokens into redundant and unique groups, then merges each redundant token with its most similar counterpart in the unique group. Furthermore, ZIPBrain serves as a training-free, plug-and-play module that seamlessly integrates into standard Transformer encoders with negligible computational overhead. Extensive experiments across multiple EEG foundation models show ZIPBrain's strong versatility, achieving 1.3%-10.5% average improvement over baselines, while reducing wall-clock inference time by 32.7% (up to 41.8% with CUDA Graph) compared to the original EEG foundation models.

Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation. We prove unconditional separations between low-depth quantum computation and the corresponding bounded-resource classical language-model architectures in both regimes. Concretely, we exhibit the following: 1. Distributional separation. We give a distribution that is sampleable by $\textsf{QNC}^0$ circuits (i.e., a family of constant-depth quantum circuits consisting of bounded fan-in gates) that no constant-round diffusion language model ($\textsf{DLM}$) with shallow scheduling and denoising can sample within constant distance, even when allowed sublinear chain-of-thought and output-token revision/remasking events, the very features modern $\textsf{DLM}$s rely on. 2. Functional separation. We exhibit a function computable in $\land \circ \textsf{QNC}^0[\log\log n]$ (i.e., a family of O$(\log\log n)$-depth $\textsf{QNC}^0$ circuits, where $n$ is the input length, followed by a single classical $\mathsf{AND}$ gate) such that any constant-depth decoder-only transformer computing the function must be large: it would have to have width $n^{Ω(1)}$. Together, our work initiates the study of quantum advantage in the era of large language models.

In this work we investigate how decoder-only transformers resolve lexical ambiguity through layer-by-layer analysis of three models spanning three parameter sizes (GPT-2-Small-117M, Llama-3.2-3B, Qwen2.5-32B). For both homonyms and polysemes, we find that representations become maximally distinct in middle layers, then partially reconverge in late layers, while the KL divergence between their next-token predictions reaches its maximum in the final layers. The activation patching experiment provides causal evidence that late-layer representational differences directly determine outputs despite apparent increased similarity in embedding space. Our single-layer ablation experiment indicates that models achieve equivalent disambiguation despite qualitatively different layer-wise vulnerabilities. These findings offer a mechanism for recent observations where models' internal embedding similarities show low correlation with their behavioural outputs despite strong performance. The semantic distinctions therefore remain present but become increasingly invisible to similarity measures over the embeddings, with implications for embedding-based methods such as semantic search, retrieval, and clustering that rely on late-layer cosine similarity.

Wearable sensors continuously capture fine-grained multivariate time-series data, providing opportunities to model behavioural patterns associated with health outcomes. However, existing deep learning methods prioritise predictive accuracy over interpretability, limiting their application in health research. In this study, we present HealthCAT, a flexible framework that integrates an Encoder-only Transformer with an Attentive Class Activation Token (AttentiveCAT) to generate class-specific, time-step-level interpretations. These interpretations can be mapped back onto behavioural cycles that are relevant to the domain (e.g., time-of-day), supporting individual-level analysis of wearable sensor data. We evaluated HealthCAT using two real-world wearable sensor datasets (306 participants in total). HealthCAT outperformed deep learning baselines by up to 17% in F1-score and 12% in accuracy on both datasets ($p<0.05$). In masking experiments, the time steps identified by HealthCAT carried significantly more predictive value than random selection across all masking conditions ($p<0.05$), indicating that the identified time steps are predictively informative. By coupling predictive performance with validated time-step-level interpretability, HealthCAT moves wearable sensor analysis beyond aggregated metrics towards temporal patterns that support health monitoring, behavioural pattern analysis, and intervention design in health research. The significance of this work is that it enables accurate prediction of health indicators from wearable sensor data while providing insights into when and how physical activity patterns occur, rather than relying solely on aggregated summary measures.

Complex structured reasoning tasks often require additional computation, yet current language models obtain it mainly by increasing parameter scale or by serializing intermediate steps as chain-of-thought (CoT) tokens. The former raises training and deployment costs, while the latter ties reasoning computation to autoregressive output length. We introduce Penelope, an efficient latent-reasoning framework for pretrained decoder-only Transformers that localizes recurrent computation to a selected decoder interval. The lower decoder prefix is evaluated once to construct a problem-conditioned boundary memory, which is then iteratively refined through time-modulated GRU dynamics and recurrent readout states before answer generation. A progressive CoT-to-latent curriculum transfers visible reasoning into this internal recurrent path, allowing additional computation to be allocated in latent space without repeatedly executing the complete decoder or generating a long intermediate trace. Experiments on open-source structured-reasoning benchmarks show that, at validation-selected latent budgets, Penelope attains competitive accuracy relative to established latent-reasoning models while reducing measured inference latency. These results show that latent refinement can be localized to a narrow decoder interval, reducing repeated full-decoder execution without generating a long visible reasoning trace and providing a practical accuracy-efficiency tradeoff for decoder-only Transformer models.

A central question in the in-context learning literature is whether transformers can organize episode-level adaptation around different inductive-bias families. We study this question in a controlled setting through latent algorithm routing: route-like behavior in which the solver-family preference changes with the latent data-generating regime while prompt form is held fixed, remains stable under nuisance perturbations, and is selectively influenced by targeted activation interventions without large losses in answer quality. We introduce ROUTEBENCH, a diagnostic benchmark whose regimes differentially favor global shrinkage, sparsity, robustness, and locality, operationalized by ridge-like, lasso-like, Huber-like, and kNN-like family representatives. Across dense decoder-only transformers trained from scratch at 44M-612M parameters, a 306M model closes 80.9 percent of the oracle-routing gap and achieves route F1 of 84.1. The effect remains substantial under natural-language renderings, shuffled supports, lexical paraphrases, and a unified four-way routing setting. Stronger adaptive alternatives, including an input-conditioned soft mixture and an unsupervised Gumbel router, narrow the gap but remain below the 306M and 612M models on route F1 and OOD performance. Probe controls and matched activation-patching controls further show that route-relevant internal directions are decodable and functionally involved in solver-family-consistent output behavior. These results provide controlled evidence that dense transformers trained on ROUTEBENCH can develop route-like internal variables, but they do not establish universal routing in pretrained language models or unrestricted natural-language reasoning.

Automated driving systems (ADSs) are becoming ubiquitous. Future Software Defined Vehicles (SDVs) may be able to run multiple ADSs, both native and aftermarket such as Comma.ai's Openpilot. Monitoring systems to independently verify which automated driving system is active are important for safety monitoring, regulatory compliance, insurance assessment, and anomaly detection. In this paper, we first evaluate the effectiveness of three sequence-based classification models: Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM) networks, and a Transformer encoder model for identifying Level 2 automated driving systems using vehicle telematics data alone: Comma Openpilot, Tesla Autopilot, and Cadillac Super Cruise, along with manual driving. All three models achieve strong clean-data performance with macro F1-scores of 0.92 (GRU), 0.90 (LSTM), and 0.93 (Transformer encoder model) when trained on clean data; threat-matched training yields 0.904-0.916 macro F1 with only a modest clean-data penalty. Second, we introduce a modular robustness evaluation framework that simulates realistic telematics degradation through five corruption families at five severity levels (L1-L5). Continuous channels are perturbed using additive white Gaussian noise with cumulative drift, correlated cross-channel noise, and temporal jitter. Binary event signals are subjected to burst loss, delayed transitions, spurious toggles and cross-feature inconsistencies inspired by communication errors. Robustness is measured using macro-F1, which gives equal weight to each class and is suitable for imbalanced multiclass evaluation. Our evaluation reveals a sharp failure-mode split: event-level corruptions reduce macro-F1 only slightly (greater than equal to 0.87 at L5), while temporal jitter collapses macro-F1 to 0.44-0.50 across GRU, LSTM, and Transformer encoder model.

This paper explores Relative Positional Encoding (RPE) as an additive bias in Transformer architectures to solve the Team Orienteering Problem. By embedding in the attention mechanism pairwise spatial relationships among nodes of the graph that represents the routing problem, the transformer encoder can compute a richer spatial-aware graph embedding that allows the decoder to estimate better routes. Experimental results involving instances up to 100 nodes demonstrate consistent improvements in collected rewards and optimality gaps over vanilla Transformer architectures used by other state-of-the-art works. These findings highlight that explicit relational modeling significantly enhances scalability and generalization for complex combinatorial optimization.

Deepfake generation has raised growing concerns regarding digital media authenticity, misinformation, identity fraud, and public trust. Recent studies show that combining spatial and frequency features leads to stronger detection results than using independently. This paper presents MSCA-FFT, a Fast Fourier Transform (FFT)-based multi-scale cross-attention framework for image-level deepfake detection. The model combines a partially fine-tuned Xception spatial branch with an FFT-based frequency branch. The frequency branch processes the log-scaled FFT magnitude spectrum through shallow convolutional layers, avoiding inverse frequency-to-image reconstruction used in DCT-based pipelines. The spatial and frequency representations are refined by transformer encoders, fused through cross-attention, and passed to an MLP classifier for real/fake prediction. Experimental results show that MSCA-FFT achieves consistently higher performance than the DCT-based state-of-the-art spatial-frequency fusion method and the compared baseline models. The ablation study further indicates that the FFT-based frequency branch provides complementary spectral cues when fused with spatial features. In addition, FFT-based frequency analysis and Grad-CAM/LIME explanations show consistent evidence around manipulation-sensitive facial regions, including the eyes, mouth, nose, and facial boundaries.

CorrNet is a strong baseline for continuous sign language recognition (CSLR) because it models inter-frame correlations inside the visual encoding stage. In this paper, we study two natural extensions of a reproduced CorrNet system: replacing the BiLSTM temporal head with a Transformer encoder, and injecting motion cues after temporal pooling. We find that the Transformer head does not outperform the BiLSTM baseline, even with a training strategy adjusted for the Transformer, and the two heads have almost the same computational and runtime cost. For the second extension, we design a lightweight module called MotionGate. In our experiments, MotionGate consistently collapses to an identity-like mapping: the gate loses motion selectivity, and the injected residual becomes a weak, non-selective perturbation of the pooled features. These results suggest that explicit motion injection after CorrNet's correlation-based encoding is largely redundant, and that natural-looking architectural extensions in CSLR should be tested carefully instead of being assumed to help.

We ask a simple question about decoder-only transformers: between which two layers is the probability of a predicted token actually produced? Existing layer-wise readout tools answer only approximately. The logit lens and its trained variant report a per-layer level of probability but give no additive decomposition; their estimates are biased and non-monotone across depth. Direct Logit Attribution and related residual-stream methods are additive, but only in logit space, the softmax nonlinearity breaks additivity in probability space, precisely the quantity one usually cares about. Layer Conductance integrates gradients per layer, but attributes each to its own baseline and so does not sum to the total change in prediction. We introduce IG-Lens, a telescoping application of Integrated Gradients along a single path through the hidden states from a baseline to the final layer. Crediting each segment to the layer it terminates at yields a layer-wise attribution whose sum is exactly the change in target probability, with the softmax inside the integration path rather than linearized away. Our default estimator credits each integration step its observed change in target probability (a prediction-aware reweighting in the spirit of IDGI) rather than its raw gradient. Because the readout is a one-dimensional probability, this collapses each segment to a telescoping sum of endpoint values, so completeness holds exactly (to floating point) at any step count, removing Riemann discretization error while suppressing steps that show gradient sensitivity without a change in output. We give the telescoping identity and its proof, verify completeness to floating point, and describe a single-pass batched implementation computing the full token-by-layer map without any backward call. Code: https://github.com/anhnda/IGLens.

Stereo-based 3D obstacle perception for autonomous driving is currently constrained by an imbalanced triplet: deployment cost, detection accuracy, and open-set adaptability. While existing methods struggle to balance these three competing objectives, there is an urgent demand for high-precision, real-time algorithms capable of detecting arbitrary obstacles in the wild. In this paper, we present DDStereo, a novel Dual-Decoder Stereo Transformer that achieves a synergistic integration of 3D object detection and Out-of-Distribution (OoD) road anomaly detection. Leveraging the geometric priors of stereo disparity, our approach effectively couples 3D attribute regression with open-set foreground detection within a streamlined dual-branch decoder architecture. Conventional methods rely on complex feature-level fusion; DDStereo maintains execution efficiency by employing a decoupled decoding strategy and shared object-level queries to ensure cross-modal target alignment. Extensive evaluations of public benchmarks demonstrate that DDStereo not only achieves state-of-the-art accuracy under open-set and closed-set protocols. Our method delivers real-time performance comparable to monocular 3D detection baselines, providing a cost-effective solution for the perception of obstacles of the normal and OoD category. Code and models are available at https://github.com/shiyi-mu/DDStereo.

Encoder-only transformer models remain essential for production NLP pipelines. We introduce moBERTo, a Portuguese adaptation of ModernBERT obtained through continued pretraining of the ModernBERT-base checkpoint on 60 billion tokens (5 epochs over a 12-billion-token corpus curated from FineWeb2 and filtered with educational and STEM classifiers). We preserve the original architecture, including rotary positional embeddings, alternating local-global attention, flash attention, and unpadding. We evaluate moBERTo across information retrieval (including long-context retrieval at up to 8,192 tokens), document classification, named entity recognition, and natural language understanding. Our best variant, which combines a Portuguese tokenizer with subword-matching embedding transfer and long-context post-training, achieves the highest average reranking nDCG@10 across three Portuguese retrieval benchmarks and the best results on PLUE-PT. Through ablation studies, we show that (i) continued pretraining is strongly preferable to training from scratch, particularly for preserving long-context capabilities; (ii) tokenizer adaptation improves token-level tasks but degrades long-context retrieval; (iii) a dedicated long-context post-training phase at 8,192 tokens further improves reranking and NER; and (iv) encoder-only architectures remain competitive with larger decoder-only alternatives for discriminative tasks. We publicly release the model weights at https://huggingface.co/Tropic-AI/moBERTo and training data at https://huggingface.co/datasets/Tropic-AI/moberto-pretraining-dataset-c4-compatible on Hugging Face.

Accurate short-term electricity demand forecasting is critical for reliable power system operation, energy market planning, and infrastructure optimization. This paper presents a hybrid framework combining a Transformer encoder for temporal feature extraction with gradient-boosted decision trees (XGBoost) for daily electricity demand forecasting across New England. The framework integrates meteorological observations from six cities spanning all six New England states, calendar and holiday effects, autoregressive demand lags, and COVID-19 epidemiological variables. Hyperparameter optimization uses Optuna with a multivariate Tree-structured Parzen Estimator over 500 trials, with a leakage-free 70/15/15 chronological train-validation-test split. The hybrid model achieves a test RMSE of 8,876 MWh, MAPE of 2.05%, and R-squared of 0.906. A tabular-only XGBoost baseline achieves RMSE of 9,304 MWh, MAPE of 2.21%, and R-squared of 0.896. A Diebold-Mariano test (Harvey-Leybourne-Newbold correction) confirms the 427.7 MWh difference is statistically indistinguishable from noise (DM = -1.126, p = 0.262). An ablation study reveals COVID-19 features improved training accuracy but had asymmetric test effects: removal degraded hybrid RMSE by 3.2% while marginally improving XGBoost-only by 1.2%. A SHAP temporal analysis shows 5 of 8 COVID features rank higher on the post-acute test set than during pandemic-active training, indicating the model over-applies learned pandemic patterns. These findings establish temporal validity decay as a central mechanism: behavioral disruptions drove a strong COVID-demand signal during 2020-2021, but adaptation was complete by mid-2022, leaving epidemiological features as noise amplifying overfitting to stale pandemic patterns.

Decoder-only Transformers compute attention over the KV cache of preceding tokens. Keys (and Values) are typically represented with the same dimensionality, regardless of its distance from the prediction target. In natural language, however, the next word is most strongly influenced by the immediately preceding tokens. We hypothesize that local and distant tokens impose asymmetric demands on representational capacity: local tokens are more critical for predicting immediate outputs and thus require richer representations, whereas distant tokens primarily serve as long-range memory, for which lower-dimensional representations may suffice. We formalize this idea as Distance-Adaptive Representation (DAR), implemented in a controlled setting that preserves full-dimensional representations within a local context window while assigning reduced-dimensional representations (e.g. 1/4 of the original dimensionality) to tokens beyond that window. Across multiple pretraining scales (70M to 410M parameters), as well as continued supervised fine-tuning on a 1B-scale model, this approach closely matches the performance of full-dimensional baselines. In contrast, uniformly reducing dimensionality across all token positions leads to worse performance. These results challenge the common assumption that key and value dimensionality should be uniform across token positions. Our findings suggest a new direction for designing attention architectures that adaptively allocate representational capacity across sequences, enabling further reductions in KV cache during inference.

The detection of gravitational waves has revolutionized our ability to explore fundamental aspects of the Universe. Traditionally, modeled gravitational-wave signals have been identified using template-based matched filtering, followed by coincidence analysis across multiple detectors in the signal-to-noise ratio time series. Recent advances in Machine Learning and Deep Learning have sparked growing interest in their application to both signal detection and parameter estimation. In this study, a hybrid Deep Learning strategy is proposed that leverages the effectiveness of Transformer encoders alongside well-established Convolutional Neural Network architectures in an attempt to estimate the intrinsic and extrinsic parameters of non-precessing binary black hole systems. The primary focus of this work is point estimation, producing single best-fit values for each parameter rather than full posterior distributions. This method is evaluated on both simulated signals embedded in Gaussian noise and real gravitational-wave events, and it demonstrates strong predictive performance and robustness across key astrophysical parameters.

Fundamental investigations into how different molecular encoding methods affect molecular property prediction remain relatively limited. In this study, we extensively examined the optimal molecular encoding methods for molecular properties prediction using two prevalent structure designs: a classical neural network model (MLP) and a Transformer encoder-based model (MLP+TL). For molecular encoding methods, we investigated several types of fingerprints, including traditional topological fingerprints, substructure-based fingerprints, and string-based representations. These two models were trained on seven well-known molecular datasets to evaluate different input molecular encoding methods based on evaluation metrics. On several biologically relevant classification tasks, including toxicity, mutagenicity, and side-effect prediction, our models consistently achieved average AUC values above 0.9. Rather than relying on external post-hoc explanation methods such as the local interpretable model-agnostic explanation (LIME) or the Deep SHapley Additive exPlanations (SHAP), we leveraged the model's intrinsic attention weights as an internal interpretability signal for identifying potentially important feature. The MLP+TL model using MACCS and PubChem as input can capture chemically interpretable groups that determined the major blood-brain barrier (BBB) permeability and mutagenicity in Salmonella typhimurium. In particular, a comparison between Morphine and Heroin highlighted the role of hydroxyl-related substructures in BBB permeability prediction, which was consistently reflected in the attention weights. Overall, our findings provide practical guidance for selecting effective molecular encoding methods and contribute to the development of interpretable molecular informatics approaches for drug discovery.

Worldwide image geo-localization aims to determine where on Earth a single image was captured. However, visually similar scenes may lie thousands of kilometers apart, so methods that localize primarily by appearance often mistake a distant look-alike for the true location. We attribute this failure to a structural cause: in existing methods, GPS coordinates serve only as training supervision, and the distance relationships among locations never enter the learned representation. To address this, we propose GeoMetric, a retrieval-based framework that encodes GPS coordinates relationally rather than in isolation, injecting the distance structure among locations into both representation learning and inference. GeoMetric comprises three components: (1) a Transformer-based GPS encoder with distance-aware location attention that modulates inter-sample aggregation by great-circle proximity; (2) a trimodal contrastive objective that aligns images, geo-textual descriptions, and GPS embeddings in a unified space; and (3) a retrieval-augmented inference stage that supplies large multimodal models (LMMs) with contrastive candidate context for grounded coordinate reasoning. Extensive experiments on IM2GPS, IM2GPS3k, YFCC4k, and YFCC26k demonstrate that GeoMetric consistently outperforms state-of-the-art methods, improving street-level accuracy (within 1 km) by 1.5%, 0.9%, 6.9%, and 2.5%, respectively. Controlled ablations confirm that the gains originate from the proposed geographic encoding rather than any specific LMM.

RoPE-trained transformers distinguish absolute position in their attention patterns, even though RoPE encodes only relative offsets in the inner product. We trace this leakage to two architectural components, The causal mask is responsible for the first: its per-query softmax denominator depends on the absolute query position by construction. The residual stream supplies the second. Under causal attention the activation at position $0$ attends only to itself and runs as a closed dynamical system from the embedding of the token at that position; downstream attention reads this trajectory through sink-reading heads. Both components appear in all three architectures we study, in architecturally specific balance: NTK scaling suppresses the residual-stream component, sliding-window attention allows it to accumulate with depth, and standard RoPE sits between. Replacing the \texttt{BOS} embedding before the forward pass removes $40\%$ of the residual-stream component at early queries. Attention sinks are token-anchored stabilizers that pass forward a deterministic fingerprint of the token at position $0$, constant across inputs when that token is the auto-prepended \texttt{BOS} and varying with it otherwise.

Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models. Yet, current approaches primarily focus on forecasting, while real-world time series are often irregularly and partially observed, requiring models that can jointly forecast, impute missing values, and handle degraded sampling conditions. To address these challenges, we introduce TS-ICL, a novel probabilistic In-Context Learning encoder--regressor Transformer that unifies forecasting and imputation. TS-ICL formulates time series tasks as timestamp-aligned regression and naturally incorporates covariates by training on synthetic dependency structures generated from a novel causal data prior. Empirically, TS-ICL achieves a new state-of-the-art in imputation, while remaining competitive with leading forecasting foundation models across both univariate and covariate-aware benchmarks. It shows particularly strong performance in forecasting with partially observed look-back windows.

Transformers consuming multi-channel scalar signals must embed $C$ simultaneous values into one $d_{\text{model}}$-dimensional vector per time step. We audit eight input encoders -- a shared-scalar baseline, per-channel linear projections, an orthogonality regulariser, a nonlinear MLP, block-partitioned concatenation, channel-independent and channel-as-token architectures, and a projected positional encoding -- on a synthetic benchmark where channel identity is informative and on ETTh1, scored by next-step negative log-likelihood. The headline is practical near-equivalence within a wide "top tier": the standard per-channel linear projection matches every alternative up to small, statistically real but practically modest differences. A direct geometric probe attributes this to a spontaneous orthogonalisation of the per-channel projections: they end up near-orthogonal with no explicit regulariser, letting the standard linear recover channel identity from the summed embedding. Two encoders lose decisively: the shared-scalar baseline collapses for information-theoretic reasons we make explicit, and the channel-independent PatchTST-spirit baseline overfits universally on the synthetic benchmark and underperforms on both. Paired tests resolve two small gaps: projecting the sinusoidal positional encoding through a learned linear layer edges the rest at small $C$ by extending this orthogonality to the positional subspace; a nonlinear MLP stem edges them at the largest $C$, with the gap shrinking under more training data. The practical recommendation: use the standard per-channel linear projection by default; reach for something more elaborate only when the task calls for it.

We present ChessMimic, a system of three small encoder-only transformers - for move, thinking-time, and outcome prediction - conditioned on the position, recent move history, player rating, and clock state. We fit a separate instance of each model per 100-Elo rating band, trading parameter efficiency for sharper per-skill calibration. On a held-out month-wide slice of Lichess Rated Blitz games ChessMimic's human move prediction accuracy outperforms Maia-2 in every Elo band. Compared to Maia-3, our 9M parameter model's accuracy sits between Maia-3-5M and Maia-3-23M without the additional complexity of Geometric Attention Bias. In addition to the move matching model, we also train a game outcome model that conditions not only on the position, but also player ratings, time control, and remaining clock times. The outcome model achieves an AUC of 0.78 out of sample, beating Maia-2 as well as logistic regressions based on material, ratings, and clock time. Finally, we train a clock model that predicts human thinking times. The clock model provides a usable but non-SOTA per-ply think-time signal under ALLIE-style filters (Pearson r = 0.41, Spearman rho = 0.50, MAE 4.10 s, against ALLIE's reported r = 0.70), with the residual gap concentrated in per-position bucket sharpness rather than bucket-marginal calibration. A public demo is at 1e4.ai and we release code, per-band weights, and the C++ data-filter pipeline code in GitHub.

Synthetic and manipulated speech can reduce the reliability of automatic speaker verification systems, so anti-spoofing methods need to be both accurate and efficient in training and inference. This paper focuses on the ASVspoof 5 Track 1 closed condition, where standard cross-entropy training may not give enough attention to hard trials and is not directly aligned with ranking- and threshold-based evaluation metrics. We propose TFPARN, a Transformer-based focal-pairwise attentive ranking network. The system extracts log-Mel features from speech, uses a Transformer encoder to model frame-level information, applies attention pooling to obtain utterance-level representations, and is trained with a combination of focal classification loss and pairwise ranking loss. RawBoost augmentation is used during training, and test-time augmentation is applied during evaluation to improve robustness. Compared with re-implemented AASIST and RawNet2 baselines under the same protocol, TFPARN achieves the best results, with a minDCF of 0.2430 and an EER of 12.52%. Ablation experiments further show that the pairwise loss, focal loss, and attention pooling all improve performance. TFPARN also uses the lowest inference memory among the compared systems, at 1.4 GB, runs at about 0.79 ms per utterance, and reaches its best checkpoint in less training time than AASIST. These results show that TFPARN provides a good balance between detection accuracy and computational cost for logical access anti-spoofing.

Watershed networks exhibit convergent topologies in which multiple tributaries merge into downstream channels,integrating diverse upstream hydrological processes. In ungauged basins, the absence of direct observations increases uncertainty and limits the ability to anticipate extreme events. This study evaluates whether an encoder-only Transformer provides an advantage over an LSTM for upstream streamflow inference under limited hydrologic information, using retrospective simulations from the NOAA National Water Model (NWM). Across both upstream-only and combined configurations, the LSTM showed stronger overall performance than the Transformer model across the two configurations. Incorporating downstream information further boosted performance for all models, increasing median NNSE by more than 60%. Rather than treating this as a leaderboard-style comparison, we interpret the experiments as a test of architectural inductive bias for hydrologic sequence inference. The results indicate that recurrent memory remains better aligned with this upstream reconstruction task than an encoder-only Transformer, while downstream hydrologic context provides a strong auxiliary constraint that substantially improves prediction skill across architectures

Positional encoding (PE) is widely viewed as necessary for transformers to process ordered sequences: without them, the next-token map appears permutation-invariant in its context tokens. This intuition underlies all prior universality results, which rely on positional information to prove that transformers with chain-of-thought can perform arbitrary computation, i.e., they are Turing complete. We revisit this belief in the regime most relevant to long-form reasoning, where generation proceeds through a finite sliding context window. Our opening perception is that the window mechanism itself (mildly) breaks the permutation symmetry. To distill and precisely capture the degree of this added expressiveness, we introduce an abstract autoregressive model, the HIST model, in which each update depends only on constant-size internal state and the token-count histogram within the current window. We prove that this HIST model is Turing complete by showing that the evolution of the window can reveal the token that has just left the window, which suffices to simulate Turing-complete Post machines. We then construct a sliding-window transformer over a constant-size token alphabet, without PE, and show that it can simulate the HIST model. Our result demonstrates that positional encodings are not indispensable for transformers to perform universal computation: The window sliding itself already breaks permutation symmetry and captures sufficient positional information.

Video Moment Retrieval (VMR) task requires accurately localizing temporal boundaries aligned with natural language queries, but many models suffer from a misalignment between continuous surrogate losses and non-differentiable metrics, leading to optimization stagnation during the late stages of training and trapping boundary predictions in suboptimal solutions. Although Reinforcement Learning (RL) post-training successfully optimizes localization results for large models, applying it directly to lightweight networks easily disrupts the fragile feature representations established during the supervised phase. To overcome this optimization bottleneck, we propose Gradient-Isolated Reinforcement Learning for DETR (GIRL-DETR), introducing RL post-training into a lightweight temporal localization framework for the first time. The input video and text features first establish early alignment through Cross-Modal Interaction (CMI) before entering the transformer encoder. Subsequently, a Text-Guided Gating (TGG) mechanism dynamically injects semantic priors into the queries before the transformer decoder generates candidate proposals, providing high signal-to-noise ratio inputs for temporal prediction. After the supervised training reaches convergence, the backbone network is frozen to protect the feature manifold, while the detection head directly optimizes the non-differentiable evaluation metric tIoU to enhance localization accuracy through a Three-stage Progressive Reinforcement Learning (TPRL) strategy. This approach achieves an orthogonal decoupling of state representation and metric optimization. Experiments on Charades-STA, QVHighlights, and TACoS demonstrate that GIRL-DETR effectively resolves surrogate loss degradation and achieves substantial accuracy improvements with minimal parameter updates, providing a robust new pathway for RL applications in lightweight VMR models.

Transformer-based architectures have advanced sequence modeling in language and vision, yet general-purpose representation learning for heterogeneous multivariate time series remains underexplored. We introduce CHARM (Channel-Aware Representation Model), which incorporates channel-level textual descriptions into a Transformer encoder equivariant to channel order. CHARM is trained with a Joint Embedding Predictive Architecture (JEPA) and a novel loss promoting informative, temporally stable embeddings; latent-space prediction encourages robustness to sensor noise while description-aware gating provides interpretability through learned inter-channel relationships. Across anomaly detection, classification, and short- and long-term forecasting, the learned embeddings achieve strong performance using only a linear probe. Performance is driven primarily by the JEPA objective and conditioning architecture, with text descriptions serving as channel identifiers for cross-dataset generalization.

Multilingual orthopedic decision support remains challenging in low-resource healthcare settings, where clinical narratives contain specialized terminology, mixed scripts, incomplete evidence, label imbalance and language-dependent documentation patterns. This article presents a reliability-oriented framework for classifying free-text orthopedic notes in English, Hindi and Punjabi. We compare task-aligned multilingual transformer encoders, a task-fine-tuned DistilBERT baseline, zero-shot instruction-tuned large language models (LLMs) and a domain-adaptive encoder, IndicBERT-HPA. IndicBERT-HPA augments IndicBERT with language-aware orthopedic adapter heads to support clinically relevant multilingual representation learning. Evaluation extends beyond aggregate accuracy to per-class performance, ROC-AUC, AUPRC, expected calibration error, cross-language stability and robustness under controlled balanced and natural-prevalence distributions. The evaluated zero-shot LLMs remain substantially less effective than task-adapted encoders for closed-set classification, with language-dependent instability. Under natural clinical prevalence, IndicBERT-HPA achieves the strongest overall performance, reaching an averaged Macro-F1 of 0.8792, Macro-AUROC of 0.894 and AUPRC of 0.902. We further implement a deterministic selective-verification layer combining confidence gating, evidence-consistency checking and language-risk screening. On a randomly selected held-out 5,000-record subset, it achieves 84.4% selective accuracy and 0.76 selective Macro-F1 at 72.3% coverage, compared with 71.5% accuracy and 0.65 Macro-F1 for accept-all prediction. These results support reliability-oriented multilingual clinical decision support with explicit deferral.

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still struggle on tasks such as long-context understanding or retrieval \cite{chen-etal-2025-hope}. Hence, a better understanding of the internal positional mechanism could help design better PE. Building on evidence that positional and semantic signals occupy nearly orthogonal subspaces in trained Transformers, we modify an encoder Transformer to process three explicitly disentangled streams: semantic, absolute positional (AP) and relative positional (RP), and confine the masked-language-modeling (MLM) objective to the semantic stream. This decoupling enables a clean mechanistic study and yields three take-aways. (1) The isolated AP subspace spontaneously collapses into a low-frequency two-dimensional manifold that captures the structure of the document; (2) Attention heads specialize into structure and semantic-oriented groups, with RP exclusively supporting the latter; (3) Standard positional encodings do not robustly retain macroscopic structure: RoPE and RP only weakly encode it, and entangled AP loses it in the final layers under MLM pressure. The disentangled approach preserves positional encoding, which improves linguistic representation on 49 of the 65 linguistic phenomena of the Flash-Holmes probing benchmark.

Electroencephalography (EEG) is a widely used non-invasive technique for measuring brain activity in brain-computer interface (BCI) applications. Supervised EEG decoding models often struggle to generalize across tasks, subjects, and datasets, motivating transformer-based EEG foundation models trained with self-supervised learning. Since transformers are permutation-invariant, they require explicit positional information. Unlike textual tokens, EEG electrodes are spatially distributed across the scalp, raising the question of how electrode positions should be encoded in transformer-based EEG models. In this study, we benchmark five positional encoding strategies within the CBraMod backbone and evaluate them under linear probing and fine-tuning protocols on motor imagery classification and emotion recognition. Our results show that no single strategy consistently outperforms across tasks. Spherical Positional Encoding (SPE) yields strong representations for motor imagery but underperforms on emotion recognition, while Asymmetric Conditional Positional Encoding (ACPE) demonstrates more consistent performance across tasks. These findings suggest that the optimal positional encoding strategy is task-dependent, with no universal solution across EEG decoding scenarios.

A central challenge in electroencephalography (EEG) foundation modeling is learning transferable representations across recordings with diverse tasks, montages, references, and spectral characteristics. Existing masked modeling approaches often rely on broadband continuous patches or a single discrete representation, which may underrepresent frequency-specific activity. This paper proposes BandVQ, a band-wise vector-quantized EEG foundation model that decomposes EEG into delta, theta, alpha, beta, and gamma bands, trains an independent VQ-VAE tokenizer for each band, and pretrains a shared Transformer encoder on the resulting discrete VQ code indices. The encoder uses masked code tokens, quantized absolute log-power tokens, channel and temporal embeddings, and metadata prefix tokens representing reference, band, task family, and phase. Region-based masking is also introduced to reduce the trivial reconstruction of spatially adjacent electrodes. The model is pretrained on 71 public EEG corpora comprising over 9,200 subjects and 357,000 single-channel hours and evaluated on six subject-independent classification datasets. Under the current evaluation setting, the proposed model achieves strong transfer performance, with the highest reported results on three cognitive tasks and competitive performance on three motor imagery tasks.

Table structure recognition (TSR) requires both table-level coherence (row/column counts, headers, spanning cells) and precise separator localization. We introduce FastTab, a grid-centric TSR model that avoids autoregressive HTML decoding by combining (i) a lightweight Tiny Recursive Module (TRM) for global reasoning and (ii) axial 1D Transformer encoders that capture long-range dependencies along rows and columns. The model predicts row/column counts, header rows, and separators to construct a grid, then infers rowspan/colspan using ROI-aligned cell features. Across four benchmarks (PubTabNet, FinTabNet, PubTables-1M, and SciTSR), FastTab achieves competitive structure recovery performance while operating at low-latency inference. We further study robustness under pixel-level anonymisation and show an extension to curved separators for camera-captured documents. The source code will be made publicly available at https://github.com/hamdilaziz/FastTab .

Real-world time series come with text: metadata, descriptions, news, reports. Yet time series foundation models process numerical sequences in isolation, and the multimodal text-and-time-series models that attempt to bridge the two all adapt a pretrained language model post hoc, inheriting representations shaped without ever seeing temporal data. These models are also evaluated almost exclusively against other multimodal baselines, not against the strongest unimodal foundation models in either domain, leaving open whether joint training is needed at all. We present Chronicle, a compact 324M-parameter decoder-only transformer trained from scratch on natural language and time series within a single unified architecture. Both modalities share the same transformer blocks, attention mechanism, and residual stream; the bulk of pretraining uses unimodal batches so cross-modal capability emerges purely from shared parameters, with a short alignment stage that interleaves the two. To our knowledge, Chronicle is the first model jointly pretrained on text and time series from scratch, and the first multimodal model evaluated against dedicated foundation models in both domains. It matches Gemma-3-270M-PT on 19 NLU tasks, sets a new bar for frozen-embedding time series classification on 24 UCR/UEA datasets, and produces multimodal forecasts on Time-MMD that beat every supervised fusion baseline, all from a single backbone.

Green hydrogen plays an essential role in decarbonization, with capacity projected to scale to 560 GW by 2030 (vs. 1.39 GW in 2023) in net-zero settings. Proton exchange membrane (PEM) electrolysis is one of the most promising technology routes to green hydrogen production, and real-time system health monitoring of PEM electrolyzers is essential for their scalable deployment. In lab settings, performance degradation can be characterized through electrochemical testing protocols by periodic pauses of normal operation. Such interruption is not practical for full-scale stack deployments, limiting system operators' ability to make real-time assessments of state-of-health (SoH). We present a machine learning (ML) framework that performs virtual electrochemical characterization during normal operation. The method uses an encoder-decoder transformer, conditioned on operational data, to reconstruct characterization outputs, focusing here on polarization curves. Inspired by patch-based sequence tokenization, we segment the inputs into patches and encode them to form meaningful tokens, which substantially improves learning efficiency. Across four longitudinal runs, lasting up to 478 hours on different test cells and loading cycles, the model accurately reconstructed polarization curves and achieved 10x reduction in mean squared error (MSE) compared to a vanilla transformer. This proof-of-concept demonstrates that ML models can enable continuous performance monitoring for PEM electrolyzers and that the encoder captures meaningful latent representations of SoH, opening up opportunities to derive interpretable indicators in future work.

Chess has long served as a canonical testbed for artificial intelligence, but modeling approaches for its central tasks have diverged. Maximizing playing strength, predicting human play, and enabling interpretability are typically solved with disparate architectures, and these designs are often misaligned with the geometry of the domain. This raises the natural question of whether these objectives require separate modeling paradigms, or if there exists a single architecture that supports them simultaneously. We introduce Chessformer, a unified architecture that advances the state of the art on all three central goals in chess modeling. Chessformer is an encoder-only transformer that represents board squares as tokens, augments self-attention with a novel dynamic positional encoding called Geometric Attention Bias (GAB) that adapts to domain-specific geometry, and predicts actions with an attention-based source-destination policy head. We evaluate Chessformer on each front. First, we develop \maiathree, a family of models for human move prediction that reaches 57.1% move-matching accuracy, significantly surpassing the previous state of the art with fewer than a quarter of the parameters. Second, we integrate Chessformer into Leela Chess Zero, a leading open-source engine, adding over 100 Elo of playing strength and resulting in tournament victories over Stockfish in major computer chess competitions. Third, we show that Chessformer's square-token design makes attention patterns and activations directly attributable to board squares, enabling granular interpretability analyses that prior architectures do not naturally support. More broadly, our results demonstrate that aligning a model's tokenization, positional encoding, and output design with the underlying structure of a domain can yield simultaneous gains in performance, human compatibility, and interpretability.

Microsimulation models used by ministries of finance and central banks rely on parametric processes for lifetime earnings that capture only first and second moments of the conditional distribution and miss long-range nonlinear structure. We propose SAGA, a decoder-only transformer for irregular tabular panel sequences, paired with a split conformal calibration wrapper that delivers individual-level prediction intervals with finite-sample marginal coverage guarantees. Trained on the longitudinal Swedish LISA register over 1990 to 2022, comprising 2,143,817 individuals and 61,284,903 person-years, the model forecasts annual labor earnings at horizons of one to thirty years and aggregates them by Monte Carlo into present-discounted lifetime earnings distributions. Against the canonical Guvenen, Karahan, Ozkan, and Song parametric process and tabular and recurrent baselines, SAGA reduces continuous ranked probability score by 31.9 percent at the ten-year horizon and mean absolute error by 37.7 percent at the twenty-year horizon. Conformal intervals achieve nominal coverage to within 0.4 percentage points marginally and within 2.4 percentage points on the worst-case demographic subgroup. The reconstructed lifetime earnings Gini coefficient is 0.327 against the partially observed truth of 0.341 and the GKOS estimate of 0.378. Model weights, calibration tables, and a synthetic equivalent dataset are released for replication outside the protected SCB MONA environment.

Decoder-only transformers compute the conditional probability of the next token from a sequence of past observations. This paper derives, from first principles, inference architectures that solve the same prediction problem - and in doing so, recovers transformer-like layer operations as a consequence of optimal control theory. The framework is developed for two model classes: a nonlinear model of discrete-valued processes, directly motivated by the transformer, and a linear Gaussian model as a tractable baseline. For both model classes, the prediction objective is reformulated as an optimal control problem whose solution yields an explicit inference algorithm, the dual filter, with a layer structure that mirrors the layer structure of a decoder-only transformer. Numerical experiments provide a comparison of the optimal control to attention weights from a trained transformer. These experiments reveal that when the embedding dimension is insufficient, the transformer implicitly exploits non-Markovian structure.

To achieve deep natural language understanding, syntactic constituent parsing plays a crucial role and is widely required by many artificial intelligence systems for processing both text and speech. A recent approach involves using standard sequence-to-sequence models to handle constituent parsing as a machine translation problem, moving away from traditional task-specific parsers. These models are typically initialized with pre-trained encoder-only language models like BERT or RoBERTa. However, the use of pre-trained encoder-decoder language models for constituency parsing has not been thoroughly explored. To bridge this gap, we extend the sequence-to-sequence framework by investigating parsers built on pre-trained encoder-decoder architectures, including BART, mBART, and T5. We fine-tune them to generate linearized parse trees and extensively evaluate them on different linearization strategies across both continuous treebanks and more complex discontinuous benchmarks. Our results demonstrate that our approach outperforms all prior sequence-to-sequence models and performs competitively with leading task-specific constituent parsers on continuous constituent parsing.

Critical events in multivariate time series, from turbine failures to cardiac arrhythmias, demand accurate prediction, yet labeled data is scarce because such events are rare and costly to annotate. We introduce HEPA (Horizon-conditioned Event Predictive Architecture), built on two key principles. First, a causal Transformer encoder is pretrained via a Joint-Embedding Predictive Architecture (JEPA): a horizon-conditioned predictor learns to forecast future representations rather than future values, forcing the encoder to capture predictable temporal dynamics from unlabeled data alone. Second, we freeze the encoder and finetune only the predictor toward the target event, producing a monotonic survival cumulative distribution function (CDF) over horizons. With fixed architecture and optimiser hyperparameters across all benchmarks, HEPA handles water contamination, cyberattack detection, volatility regimes, and eight further event types across 11 domains, exceeding leading time-series architectures including PatchTST, iTransformer, MAE, and Chronos-2 on at least 10 of 14 benchmarks, with an order of magnitude fewer tuned parameters and, on lifecycle datasets, an order of magnitude less labeled data.

Transformers with self-attention modules as their core components have become an integral architecture in modern large language and foundation models. In this paper, we study the evolution of tokens in deep encoder-only transformers at inference time which is described in the large-token limit by a mean-field continuity equation. Leveraging ideas from the convergence analysis of interacting multi-particle systems, with particles corresponding to tokens, we prove that the token distribution rapidly concentrates onto the push-forward of the initial distribution under a projection map induced by the key, query, and value matrices, and remains metastable for moderate times. Specifically, we show that the Wasserstein distance of the two distributions scales like $\sqrt{{\log(β+1)}/β}\exp(Ct)+\exp(-ct)$ in terms of the temperature parameter $β^{-1}\to 0$ and inference time $t\geq 0$. For the proof, we establish Lyapunov-type estimates for the zero-temperature equation, identify its limit as $t\to\infty$, and employ a stability estimate in Wasserstein space together with a quantitative Laplace principle to couple the two equations. Our result implies that for time scales of order $\logβ$ the token distribution concentrates at the identified limiting distribution. Numerical experiments confirm this and, beyond that, complement our theory by showing that for finite $β$ and large $t$ the dynamics enter a different terminal phase, dominated by the spectrum of the value matrix.

We study causal self-attention dynamics -- a toy model for decoder Transformers -- which we interpret as a non-exchangeable interacting particle system. Adapting cumulant expansions to the triangular causal dependency structure of the model, and appealing to non-hierarchical methods to estimate correlations using Glauber calculus, we prove a quantitative mean-field limit result and a next-order characterization of correlations. For iid uniformly distributed tokens, the limiting correlation equation can be solved in closed form and we obtain a rigorous explanation of the empirically observed \emph{lost-in-the-middle} phenomenon: the token retrieval profile, as a function of the source position in the prompt, is $\mathsf{U}$-shaped, with primacy, recency, and a unique interior minimum under an explicit smallness condition.

Understanding how linguistic structure emerges in language models is central to interpreting what these systems learn from data and how much supervision they truly require. In particular, semantic role understanding ("who did what to whom") is a core component of meaning representation, yet it remains unclear whether it arises from pre-training alone or depends on task-specific fine-tuning. We study whether semantic role understanding emerges during language model pre-training or requires task-specific fine-tuning. We freeze decoder-only transformers and train linear probes to extract semantic roles, using performance to infer whether role information is already encoded in pre-training or learned during adaptation. Across model scales, we find that frozen representations contain substantial semantic role information, with performance improving but not fully matching fine-tuned models. This indicates partial but incomplete emergence from pre-training alone. We show that semantic role structure emerges from language modeling objectives, but its internal implementation shifts toward more distributed representations as model scale increases.

We give a novel logical characterization of encoder-decoder transformers, the foundational architecture for LLMs that also sees use in various settings that benefit from cross-attention. We study such transformers over text in the practical setting of floating-point numbers and soft-attention, characterizing them with a new temporal logic. This logic extends propositional logic with a counting global modality over the encoder input and a past modality over the decoder input. We also give an additional characterization of such transformers via a type of distributed automata, and show that our results are not limited to the specific choices in the architecture and can account for changes in, e.g., masking. Finally, we discuss encoder-decoder transformers in the autoregressive setting.

We analyse the computational power of transformer encoders as sequence-to-sequence functions on vectors. We show that average hard attention can be used to simulate arithmetic circuits if they are given as an input to an encoder. The circuit families that can be simulated this way have constant depth while using unbounded addition, binary multiplication and sign gates. The transformers we use have arithmetic circuits instead of feed-forward networks. With typical average attention the functions they compute are also computed by the same class of circuit families. Our results hold for transformers over the reals, rationals and any ring in between the two.

Generative models trained on synthetic plan data are a promising approach to generalized planning. Recent work has focused on finding any valid plan, rather than a high-quality solution. We address the challenge of producing high-quality plans, a computationally hard problem, in sub-exponential time. First, we demonstrate that, given optimal data, a decoder-only transformer can generate high-quality plans for unseen problem instances. Second, we show how to self-improve an initial model trained on sub-optimal data. Each round of self-improvement combines multiple model calls with graph search to generate improved plans, used for model fine-tuning. An experimental study on four domains: Blocksworld, Logistics, Labyrinth, and Sokoban, shows on average a 30% reduction in plan length over the source symbolic planner, with over 80% of plans being optimal, where the optimum is known. Plan quality is further improved by inference-time search. The model's latency scales sub-exponentially in contrast to the satisficing and optimal symbolic planners to which we compare. Together, these results suggest that self-improvement with generative models offers a scalable approach for high-quality plan generation.

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is particularly acute for transformer-based language models, where training is expensive, models are often reused in frozen form, and poorly optimized layers can silently degrade performance. We propose a layer-wise peeling framework for monitoring training dynamics, in which each transformer layer is locally optimized against intermediate representations of the trained model. By constructing lightweight, layer-specific reference solutions and projecting layers onto multiple intermediate outputs via different permutations, we obtain achievable baselines that enable fine-grained diagnosis of under-optimized layers. Experiments on decoder-only transformer models show that these layer-wise reference bounds can match or even surpass the trained model at various stages of training, exposing inefficiencies that remain hidden in aggregate loss curves. We further demonstrate that this analysis remains effective under binarization and quantized settings, where training dynamics are particularly fragile. Across all numerical results, the proposed bounds consistently separate apparent convergence from effective optimality, highlighting optimization opportunities that are invisible when relying on training loss alone.

Operational weather prediction has long relied on physics-based numerical weather prediction (NWP), whose accuracy comes at the cost of substantial compute and complex simulation workflows. Recent transformer-based forecasters offer efficient data-driven alternatives, however transformers are physics-agnostic models. Additionally, standard transformer encoders evolve representations through discrete layer updates that may be less suited to modeling smooth latent dynamics. In this work, we propose a continuous-depth transformer encoder for weather forecasting that integrates Neural Ordinary Differential Equation (Neural ODE) dynamics within each encoder block. Specifically, we replace discrete residual updates with ODE-based updates solved using adaptive numerical integration. We also introduce a two-branch attention module that combines conventional patch-wise self-attention with an auxiliary branch that applies a derivative operator to attention logits, providing an additional change-sensitive interaction signal. To further align forecasts with governing principles, we propose a customized physics-informed training objective that enforces physical consistency as a soft constraint. We evaluate the proposed method against a standard discrete transformer baseline and an existing continuous-time Neural ODE forecasting variant, demonstrating the importance of PINN-Cast in short term weather forecasting.

We describe our system for SemEval-2026 Task 6 (CLARITY: Unmasking Political Question Evasions), which classifies English political interview responses by coarse-grained clarity (3-way) and fine-grained evasion strategy (9-way). Since responses frequently exceed the 512-token limit of standard Transformer encoders, we apply an overlapping sliding-window chunking strategy with element-wise Max-Pooling aggregation over chunk representations. A shared RoBERTa-large encoder supplies two task-specific heads trained jointly via a multi-task objective, with inference-time ensembling over 7-fold stratified cross-validation. Our system achieves a Macro-F1 of 0.80 on Subtask 1 and 0.51 on Subtask 2, ranking 11th in both subtasks.

We investigate whether the Feed-Forward Network (FFN) sublayer in a decoder-only transformer can be replaced by an explicit learned memory graph while preserving the surrounding autoregressive architecture. The proposed Graph Memory Transformer (GMT) keeps causal self-attention intact, but replaces the usual per-token FFN transformation with a memory cell that routes token representations over a learned bank of centroids connected by a learned directed transition matrix. In the base GMT v7 instantiation studied here, each of 16 transformer blocks contains 128 centroids, a 128 * 128 edge matrix, gravitational source routing, token-conditioned target selection, and a gated displacement readout. The cell therefore returns movement from an estimated source memory state toward a target memory state, rather than a retrieved value. The resulting model is a fully decoder-only language model with 82.2M trainable parameters and no dense FFN sublayers, compared with a 103.0M-parameter dense GPT-style baseline used in the evaluation. The base v7 model trains stably and exposes centroid usage, transition structure, and source-to-target movement as directly inspectable quantities of the forward computation. It remains behind the larger dense baseline in validation loss and perplexity (3.5995/36.58 vs. 3.2903/26.85), while showing close zero-shot benchmark behavior under the evaluated setting. These results are not intended as a state-of-the-art claim; they support the viability and structural interpretability of replacing dense within-token transformation with graph-mediated memory navigation. Broader scaling, optimized kernels, and more extensive benchmark evaluation are left for subsequent work.

Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the validity of backtests and causal inference in finance and the social sciences. Point-in-time language models--trained exclusively on text available up to each calendar date--eliminate this leakage by construction, but existing efforts typically produce models that lag substantially behind their unconstrained counterparts. We show that this performance gap can be substantially narrowed through scale. Training decoder-only transformers with up to 4 billion parameters on 1 trillion chronologically filtered tokens from FineWeb, we construct a sequence of monthly model checkpoints spanning 2013-2024. Across a range of common-sense reasoning and language understanding benchmarks, our models approach the performance of leading open-weight models of comparable size (e.g., Gemma-3-4B and LLaMA-7B) trained on temporally unrestricted data, although a performance gap remains on several tasks. Instruction fine-tuning via LoRA further improves downstream usability. We release the complete pipeline--including dataset construction, training infrastructure, and evaluation code--to enable reproducible point-in-time language modeling and to support research applications that require strict temporal validity.

We investigate the ability of decoder-only transformer models to perform abstract symbolic reasoning; specifically solving propositional logic reasoning problems given in-context. Previous work demonstrated that models fail to generalize to problems involving variable names that were not observed during training, and it was shown that one reason behind this is the difficulty of copying (or generating) unseen tokens. We show both theoretically and empirically that a particular representational collapse also has a crucial role: the unembeddings (last-layer weights) of unseen tokens collapse to nearly the same vector during training. The collapse makes distinguishing multiple unseen variables difficult for the model (especially when the embedding and unembedding parameters are shared), and provides a mechanistic explanation for the effectiveness of existing heuristic interventions like "active forgetting", which periodically reset the token (un)embeddings. Based on these observations, we devise a combination of techniques, involving a small architecture change facilitating copying, data diversity, and freezing or resetting (un)embeddings, that achieves generalization to unseen tokens. We support our claims with extensive controlled experiments on propositional logic reasoning problems. Beyond synthetic experiments, we also observe evidence of (un)embedding collapse in the open-weight models in the Gemma 3 family, which includes 99 unused tokens reserved for downstream use. Empirically we find that the correlated embeddings of these tokens are a poor initialization for finetuning applications.

Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain priors. This keeps the field isolated from the broader Transformer ecosystem, limiting the transfer of new advances as well as the benefits of increasingly optimized software and hardware stacks. To bridge this gap, we adapt the vanilla Transformer encoder to 3D scenes with minimal modifications. Given an input 3D scene, we partition it into volumetric patch tokens, process them with full global self-attention, and inject positional information via a 3D extension of rotary positional embeddings. We call the resulting model the Volume Transformer (Volt) and apply it to 3D semantic segmentation. Naively training Volt on standard 3D benchmarks leads to shortcut learning, highlighting the limited scale of current 3D supervision. To overcome this, we introduce a data-efficient training recipe based on strong 3D augmentations, regularization, and distillation from a convolutional teacher, making Volt competitive with state-of-the-art methods. We then scale supervision through joint training on multiple datasets and show that Volt benefits more from increased scale than domain-specific 3D backbones, achieving state-of-the-art results across indoor and outdoor datasets. Finally, when used as a drop-in backbone in a standard 3D instance segmentation pipeline, Volt again sets a new state of the art, highlighting its potential as a simple, scalable, general-purpose backbone for 3D scene understanding.