Foundation models pretrained on large natural-image collections are increasingly adapted for medical image segmentation, in the expectation that they will replace models trained for each task. Most comparisons, however, use data from the training distribution and a single task-specific baseline whose configuration is rarely justified, and therefore provide limited evidence of performance at new clinical sites. It also remains unclear how much of a foundation model must be adapted, and what determines this. We adapted a foundation model, DINOv2, with strategies ranging from tuning only its bias terms to full fine-tuning, and compared it with U-Nets and ResU-Nets trained from scratch. Experiments covered colonoscopy, breast ultrasound and dermoscopy, with testing on held-out data from the training source and on independent datasets from other institutions. The adapted foundation model generalised better on every external dataset. Within the training distribution, the task-specific models remained competitive when training data were abundant, and delineated boundaries more precisely, while the foundation model more often missed small lesions. Only a small fraction of the foundation model required adaptation, and the capacity needed was determined by the imaging domain rather than by the adaptation method. A widely used polyp test set was also found to duplicate images from another benchmark. Foundation-model adaptation is therefore warranted where models must work across sites, with capacity selected on the target domain.
DeepLearning (DL)-based Computer-Aided Diagnostic (CAD) systems have shown great promise in supporting clinicians, but their performance heavily depends on the availability of large, well-annotated datasets. In medical lesion detection, the scarcity of comprehensive, stan dardized annotations and the heterogeneity of existing datasets limit the development of robust foundation models. In this work, we introduce a novel approach to building a multi-domain foundation model for le sion detection by integrating diverse medical image datasets annotated for both anatomical structures and abnormalities. We first propose a student-teacher training strategy to effectively combine datasets with heterogeneous label spaces, mitigating catastrophic forgetting, and im proving feature learning. In addition, building on our previously pro posed example-based EM-DETR framework, we adapt it to jointly learn from multiple domain-specific datasets, enabling fine-grained, example driven detection across modalities. Our model achieves state-of-the-art (SOTA) results, with image-level AUC scores exceeding previous SOTA by 1% point on four key findings in CXRs. We achieve a leading mAP50 in CXRs and mammography, surpassing EM-DETR trained on a single dataset by 2-3% points. This approach paves the way for scalable foundation models in medical imaging that leverage heterogeneous data while maintaining robust and generalizable performance.
We present TorchCurves, a PyTorch library that treats vector-valued parametric curves as learnable primitives. Its central operation maps batches of scalar inputs to points on curves represented in B-spline or Legendre polynomial bases, with differentiation through both inputs and coefficients. Curve coefficients can be optimized jointly with the surrounding model or produced by another network. The library provides trainable modules, reusable basis modules, and a functional interface, supporting applications ranging from continuous feature embeddings to Kolmogorov-Arnold networks and functional regression. Its implementation combines classical evaluation algorithms with vectorized PyTorch operations, emphasizing readability and maintainability without custom hardware kernels. Timing experiments compare curve evaluation against NumPy and SciPy and KAN training against EfficientKAN across a range of problem sizes. The results illustrate where this generality remains computationally practical and where overhead is substantial. Library is available on GitHub at https://github.com/alexshtf/torchcurves.
Reinforcement learning with verifiable rewards (RLVR) produces rich training experience, yet outcome rewards reduce each attempt to a single number and leave most of this information unused. Training-time scaffolds, such as strategies or hints added to the prompt during training, offer a natural way to turn this information into guidance, but their design and adaptation are largely left to humans and tailored to specific domains. We introduce AutoScaffold, a unified AI-for-AI framework that turns a student's training experience into adaptive scaffolds, with minimal domain-specific information and no human intervention during training. A frozen teacher periodically examines this experience, diagnoses bottlenecks, and designs scaffolds in two forms: (i) strategies shared across a class of tasks and (ii) hints for individual hard tasks, adjusting the content and amount of support as the student learns. The scaffolds are removed at evaluation. We apply the same framework to ALFWorld, search-based QA, mathematical reasoning, and GPU kernel generation. When evaluated without scaffolds, students trained with AutoScaffold outperform those trained with the corresponding RL baselines in all four domains, with gains of 7.2 points in ALFWorld success and 4.0 points in average QA exact match. On GPU kernel generation, AutoScaffold increases the fraction of tasks with a correct kernel that runs faster than the PyTorch reference by up to 5.0 points. On math, our student surpasses QuestA's reported accuracy using approximately one-third as many student training steps. Analyses show that the teacher identifies a different failure in each task class and shifts its scaffolds from step-by-step workflows to targeted fixes as the student improves, and that its revised scaffolds help the student learn more than keeping the previous scaffold or using no scaffold.
LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternative the evidence supports. To recover that alternative, we introduce Contrastive Discovery, which replaces the single hypothesis with a contrast set, a scientific question paired with mutually exclusive and collectively exhaustive competing explanations. Each experiment is scored by how its evidence redistributes belief across the set, and the question is resolved when belief concentrates on one explanation. Because contrast sets change only the unit an agent proposes and scores, an existing agent can use them to re-evaluate evidence it has already collected or to guide its search. Across six domains, $89\%$ of the pointwise candidates with the largest belief shifts are rejections. On the same evidence, contrast sets resolve $73\%$ of these candidates to a specific alternative. When contrast sets guide search, the agent resolves $67\%$ more questions than pointwise surprisal under the same experiment budget. In a blinded study, $38$ human experts chose the same explanation on $78\%$ of resolved questions and on $82\%$ of questions where the pointwise agent rejected its hypothesis and stopped. Together, these results support explicit competing explanations as a way for discovery agents to resolve more scientific questions from the same evidence and validation budget.
Predicting how a ligand binds to its target is central to small-molecule drug discovery. Modern cofolding models can generate diverse candidate poses, but reliably ranking these candidates remains challenging. We introduce Pyrite, a pairwise pose-ranking benchmark comprising 1,500 pose pairs across diverse protein-ligand complexes. Expert chemists equipped with 3D visualization tools and physics-based scores perform near chance, highlighting the difficulty of interpreting available chemical signals. To investigate automated ranking, we introduce PyriteRep, a structured representation of molecular geometry, protein-ligand interactions, and physicochemical scores, and develop two LLM-based agents: PyriteReasoner, which directly compares poses through text-based reasoning, and PyriteFeaturizer, which generates executable code to construct features for logistic regression, optionally incorporating features derived from LLM subcalls. These agents achieve up to 67% and 74% accuracy, respectively, exceeding observed expert performance. LLM-guided feature discovery generally outperforms direct reasoning, while Group Relative Policy Optimization (GRPO) improves open-weight models, enabling them to match or surpass closed-source frontier models in our evaluations. These results establish Pyrite as a challenging test of pose-ranking ability and highlight LLM-guided feature discovery as a promising approach to interpret and combine the outputs of computational chemistry tools.
Connectome-constrained models are often used to argue that a measured wiring diagram outperforms shuffled or rewired wiring, and hence that structure shapes function. Such comparisons can confound wiring with how the models are tuned: a connectome fixes who connects to whom, not the excitability, gains or plasticity rates the model also needs, and modellers often tune these until the real-wiring model works. We separate three estimands: physiology tuned on the real wiring and transferred to nulls (P1), each wiring tuned on its own (P2), and P2 restricted to physiology consistent with independent data (P3). The biases involved are known in machine learning (under-tuned baselines, inherited weights, winner's curse); we measure what they do to biological conclusions, using synthetic ground truth, placebo nulls and three Drosophila circuit models. Some claims survive every protocol we test: segregated reward and punishment dopamine improves learning, and head-direction topography is required for a persistent bump. Others do not. In the mushroom body, the real Kenyon-cell output wiring beats a cross-subtype identity shuffle by 0.09 under P1 and P2 but loses to it by 0.09 under P3 (95% CIs exclude zero; held-out runs confirm). The verdict is set by the share of alpha'beta' cells among active Kenyon cells, which P1 selects low; at the share implied by imaging (about 44%) the real-wiring model fails to learn, exposing a model inadequacy rather than a deficit of the fly's wiring. In flyvis, P1 penalises a mirrored connectome, which has a constructed solution within 0.07 (median) of the real error, more than a spatially shuffled one in 50 of 50 members; the ranking survives ten-fold longer retraining but depends on the checkpoint at fifty-fold. A credible structural claim needs matched optimisation, data-constrained physiology and a model that still works there.
Agent harnesses have emerged as a promising mechanism for continual learning, alongside test-time parametric learning. However, the current benchmarks have several limitations: they generally focus on a single applied domain, serve each instance only once, and assume a single family of learner, so memory-based and weight-based systems are rarely compared on the same scale. We propose Continual-ARC, a lifelong stream built from the three ARC-AGI editions, whose tasks need no domain knowledge. The same tasks return after dormant gaps with fresh instances, while new tasks keep arriving. On each instance, the learner may pay for demonstrations, submit answers, or act inside the harness, with retries permitted on incorrect submissions, which are paid for. Each instance is scored based on the share of this feedback budget consumed. Since a learner may keep anything between instances, memory-based and weight-based systems are scored on the same scale. After the stream, the learner is frozen and tested on fresh instances of the tasks it met, which measures memorization, and on unseen tasks, which measures generalization. We run an agent harness with frozen weights, with and without persistence, on Qwen3.5-9B and GLM-5.3 Flash, comparing them with two prompting floors, a program-induction method and Qwen3.5-9B's weights trained to imitate GLM-5.3 Flash. Persistence in the harness generally does not improve memorization unless provided with explicit expert guidance. Most harness-based methods still learn less than a floor that simply caches each task's demonstrations, across all models we tested. No harness-based method gains on unseen tasks, whereas weight-based learning shows substantial gains. This opens the door to future weight-based continual learning that could teach models to drive harnesses in new domains.
Foundation models trained on large unlabeled corpora develop emergent capabilities, tasks that go beyond the training objective. We extend this paradigm to multimodal biology with Bonbon, a foundation model for molecular interactions trained on approximately 3.2 trillion tokens of paired protein-ligand sequences. From a single representation space, Bonbon exhibits three zero-shot emergent capabilities at hierarchical levels of resolution: functional (mechanism of action), residue (binding site localization, including orthosteric/allosteric discrimination), and bond (covalent versus non-covalent engagement). All three capabilities generalize to out-of-distribution complexes. Bonbon was trained on protein-ligand sequences alone, without any task-specific supervision and without structural coordinates. We conducted controlled scaling experiments across six model scales from 42M to 1.6B parameters; every capability evaluated shows a sharp jump at the largest scale on continuous metrics, even as pretraining loss decreases smoothly. This demonstrates that loss-based scaling laws alone are insufficient to predict when zero-shot emergent capabilities become available. The capabilities reported here emerge after training at a 1:2,000 parameter-to-token ratio to accommodate the sparsity of paired biological interaction data. The same frozen representations achieve state-of-the-art binding and affinity prediction at five orders of magnitude greater speed than co-folding methods. In prospective wet-lab validation across nine disease targets spanning seven protein families, Bonbon achieves a 61.5% dose-response hit rate on de novo compounds, yielding structurally novel molecules not previously reported to inhibit these proteins, including for out-of-distribution targets.
Biological visual systems compute reliably under tight metabolic and wiring constraints, whereas artificial vision systems consume far more energy and can be sensitive to adversarial perturbations. Whether networks with brain-like wiring are more robust at lower computational cost is unclear. We address this by benchmarking a task-optimized, continuous-time recurrent neural network of the fly visual system constrained by its synaptic connectome (FlyNet) against artificial neural networks. We compare it against CNNs, RAFT, and continuous-time recurrent neural networks without detailed connectome constraints (sCTRNN, CTRNN) on a collision-detection task within a differentiable 3D rendering pipeline. FlyNet is adversarially vulnerable but, relative to its compute, more robust to common video corruptions than RAFT, while using up to five orders of magnitude fewer FLOPs. The CTRNNs remain more robust than FlyNet across almost all tested perturbations, suggesting that connectome constraints benefit efficiency, through their low edge count, over robustness. Recurrence improves robustness to white-box attacks in RAFT and temporal context improves robustness to common corruptions. FlyNet's position and velocity representations degrade under adversarial textures but recover under counterfactual textures that restore correct classification while staying equally far from training, ruling out unfamiliar textures as the cause of failure. The reverse-phi illusion similarly disrupts these representations and inverts the same low-level motion statistic as the adversarial textures. Optimizing this input statistic alone, without access to the network, suffices to induce classification failure, attributing both perturbations to the same circuit vulnerability. Connectome-constrained models can thus surface adversarial failure mechanisms as testable hypotheses about biological perceptual vulnerabilities.
Cross-sensor remote sensing image retrieval aims to find scenes with the same content across heterogeneous sensors, such as SAR and optical or panchromatic (PAN) and multispectral (MS) imagery, without manual labels. Existing self-supervised methods either reconstruct sensor-specific pixel detail, align each image only with its co-registered twin, or rely on large transformers with 118-173M parameters (and up to 398M). We introduce RS-JEPA, a compact joint-embedding predictive framework built on a Vision Mamba encoder shared by both sensors. Since a state-space encoder reads an image as an ordered sequence of patches, we propose scan-path views, which treat two reading orders of the same image as two views with identical pixels and predict the hidden patches in one order from the visible patches in the other.To keep this prediction challenging, we propose Adversarial View Coupling (AVC), which learns the hardest split of the visible patches, and a neighbourhood consensus loss that aligns the scene similarities of both sensors. Extensive experiments on SAR-optical (BEN-14K, CBRSIR-VS) and PAN-MS (DSRSID) benchmarks demonstrate that RS-JEPA achieves the highest F1@5 among twelve re-implemented methods (72.92, 80.35 and 94.43) with a retrieval network of only 3.88M parameters (14.57M in training, 8-16times fewer than prior JEPA retrievers). Like prior methods, RS-JEPA trains on co-registered pairs. Our results highlight reading order as a source of self-supervised views. code: https://github.com/Tanishq251/RSJEPA.
Deploying LLM-based analytics agents in enterprise settings requires evaluation frameworks that can reliably detect failures across complex, multi-tool workflows. We present a three-phase comparative study of three evaluation frameworks, each representing a distinct evaluation paradigm (trace-based LLM judging, text-only LLM judging with red-teaming, and deterministic heuristics), applied to two analytics agents in a controlled research setting using frozen execution traces. Phase 1 quantifies evaluation harness stability through repeated measurements, finding that 97% of configurations meet the stability threshold and that stability patterns are agent-independent. Phase 2 measures known risk detection on 72 ground-truth test cases, where the trace-based framework achieves the best precision-recall balance (F1=0.90) while text-only evaluation matches on recall but generates 5x more false alarms. Phase 3 evaluates unknown risk discovery, uncovering 24 novel failures with zero overlap between functional testing and security red-teaming. Our results demonstrate that (1) the information available to the evaluation harness determines evaluation quality, (2) functional and security evaluation are complementary, and (3) LLM-based evaluation harnesses surface subtle errors that human reviewers miss. We recommend a two-framework strategy: trace-based evaluation for functional assessment and adversarial red-teaming for security validation.
Business process automation runs the same Standard Operating Procedure (SOP) again and again on new inputs. Large Language Model (LLM) agents can follow an SOP written in natural language, but they call an LLM to choose every step of every run, which adds latency and cost at scale. We present ReTrace, which turns an SOP and a few logged agent runs into a reusable workflow in which code, not an LLM, selects the next step. The agent's reasoning, the explanation it writes with each tool call, often states why it took an action; the tool calls alone do not. ReTrace extracts the condition behind each step, merges these conditions across runs into a compact rule document, and generates an executable workflow from it. Only this last stage depends on the platform, so rule documents can be compiled for different orchestration platforms. On $79$ procedures from our production platform, ReTrace workflows reach $93.8\%$ completion, against $96.8\%$ for the agent, at $24\%$ lower cost per task. On $\tau^2$-Bench, they reach $75.8\%$ task success (agent: $80.6\%$) and run in $1.3$s instead of $170$s; three rounds of repair on training failures lift $k{=}2$ workflows from $66.7\%$ to $81.2\%$. On eight SOP-Bench procedures, ReTrace without repair trails few-shot generation ($80.6\%$ vs. $83.6\%$), but repair from labeled training failures lifts it to $87.8\%$ at $0.40$s per task, compared to $85.5\%$ in $46.6$s for the agent.
Time series analytics has been widely applied across various domains. While existing time series foundation models (TSFMs) have demonstrated promising results, they still face two major challenges: 1) Most TSFMs mainly rely on stacking Transformer layers to increase parameter size, lacking the ability to adaptively model complex time series patterns from multi-domain data. 2) Current TSFMs are primarily pre-trained for specific tasks, e.g., forecasting or anomaly detection, and a few models support multiple tasks, but they fail to fully leverage task specificity and commonality, resulting in suboptimal performance. To address these challenges, we propose TimeSeek, a novel generalized time series analytics model that adaptively models time series patterns from multi-domain data and unifies multiple tasks in pre-training. Conceptually, TimeSeek is guided by selective information sharing under domain and task heterogeneity. From the perspective of multi-domain data, we propose a Multi-Domain Feature Extractor that adaptively captures temporal dependencies and channel correlations based on domain-specific characteristics, including progressive multi-scale modeling and adaptive slot channel modeling. From the perspective of the diversity of tasks, we propose multi-task collaborative training, which leverages task specificity and task commonality through task customization and cross-task training, effectively unifying multiple tasks in pre-training and better adapting to diverse downstream scenarios. After pre-training on large-scale time series data, TimeSeek achieves state-of-the-art performance in forecasting, anomaly detection, and classification tasks across both few-shot learning and zero-shot situations, together with favorable inference efficiency.
Research ideation is iterative: researchers refine their ideas step by step based on feedback. Yet existing evaluations obscure this search process, making it difficult to understand how LLMs explore the space of research ideas and what limits their progress. We introduce Re-Search, which adapts the format of Twenty Questions to research ideation: given only the research problem of a published paper, a model must rediscover the paper's core idea by asking yes-or-no questions. Built from 200 ICML 2026 papers, Re-Search tracks how a model's idea evolves as it asks questions and receives binary oracle feedback, isolating ideation from execution. Across six recent LLMs, nearly all progress happens within the first 30 of 100 questions, which largely decide how the game ends; after that, most models plateau. Through controlled interventions on the candidate questions and the hypothesis space, we find that the bottleneck is generation, not judgment: models recognize a good idea or a good question when one is offered, but often cannot produce it on their own. We further analyze the ideation traces and find that models fail by either over-exploiting one direction or over-exploring too many. These findings point to concrete design principles for autoresearch systems: since models can judge candidates they cannot produce, enriching the search with externally sourced ideas and questions may be more effective than improving any single model's generation ability.
Neural networks are increasingly studied not merely as predictive systems, but as complex systems whose internal computations are themselves objects of scientific inquiry. Recent progress in mechanistic interpretability (MI) has made it possible to identify neurons, features, circuits, population structures, and dynamical patterns associated with model behavior. As these tools improve, attention is shifting from what can be observed inside a model to how those observations support mechanistic explanations. We examine the parallel efforts of neuroscience and MI to address this question and identify recurring inferential bottlenecks when inferring mechanisms from complex neural systems. We propose five principles and organize them into a recursive logic for a more rigorous procedure of mechanistic inference. These principles provide a framework that supports scientific discovery in two senses: it helps turn local interpretability findings into cumulative knowledge of mechanisms within models, and it makes those mechanisms sufficiently precise to generate testable hypotheses about domains beyond the models. Evidence beyond MI is ultimately required to establish what model mechanisms reveal about the world.
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.
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.
Computer vision offers a scalable, non-contact means of estimating livestock traits, but correlated images and video frames make reliable evaluation difficult. Image-random splitting can place views of the same animal in both training and test sets, while deployment further requires transfer to animals captured in future years. We introduce BoviShift, a corpus reconstructed from six consecutive annual cohorts of an operational cattle marketplace collected from 2021 to 2026. It contains 2{,}657 cattle, 10{,}610 still images, and 2{,}566 walk-around videos across nine recorded breed categories. We evaluate three splitting strategies through four configurations: image-random and pooled cattle-disjoint splits over the same development cohorts, followed by separate future-2025 and locked future-2026 evaluations. Using a fixed ResNet-50 multi-task baseline, we assess weight, age, height, breed, and coat color. Differences between image-random and cattle-disjoint splitting are task-dependent rather than a universal leakage penalty. Future-cohort behavior is also attribute- and cohort-specific: breed declines relative to pooled evaluation; mean weight and age performance fails to beat constant baselines in 2025; height remains above baseline; and color transfers well to 2025 but degrades in 2026. Multi-task training improves all five point estimates in a single-seed ablation, still-view aggregation helps selectively, and zero-shot video-frame aggregation exposes a still-to-video domain gap. To our knowledge, BoviShift is the longest-spanning cattle-vision resource combining consecutive annual cohorts with physical and visual attributes.
Preventing human error in physical assembly tasks requires assistance systems that can intervene before mistakes are made. This is especially challenging in settings where users are free to choose the construction order and correctness depends on the evolving assembly rather than a fixed next step. We present TanCRAFT, a four-stage real-time predictive assistance system that tracks the scene state, reasons about the current partial assembly, forecasts the near-future motion of manipulated pieces, and intervenes when the predicted placement is incompatible with the target. We instantiate our framework and confirm its effectiveness in a controlled tangram assembly task through offline benchmarks and a within-subject user study. Our findings show that the predictive feedback significantly reduces mistakes relative to unguided and reactive sessions, while yielding the lowest mean perceived workload and shortest mean completion time. Overall, these results demonstrate the value of predictive feedback for error prevention and provide a step toward cost-aware assistance for automation and human-robot workcells.