Curriculum Learning

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 93

Oct 7, 2026cs.CV

When to Unpair: Regulating Pairing Dependence in Medical Visual In-Context Learning

Visual in-context learning (ICL), well suited to label-scarce medical imaging, uses support image-label pairs to demonstrate input-output mappings, while the labels collectively indicate the requested task. We diagnose dependence on individual pairings with a test-time derangement that reassigns every support label to another support image while preserving the query, support images, and label multiset. The resulting pairing gap, defined as shuffled-minus-matched performance, shows that all four released models depend on the pairing, to widely varying degrees. Further analysis of a paired-trained model reveals support-associated spurious regions and lesion-size biases even with real, unaltered supports, alongside sensitivity to mis-registered support labels. To regulate this dependence, we introduce a late unpairing curriculum (LUC), which starts with matched training and then applies random unpairing, replacing each support label with that of another support in the same episode. LUC nearly closes the pairing gap on two backbones while maintaining or improving matched-support performance across all evaluated task types, with gains extending to held-out tasks and cross-dataset episodes. It also mitigates these failure modes. On BraTS whole-tumor segmentation, matched-support DSC rises from 0.733 to 0.857 while the gap shrinks from -0.184 to -0.008. In a released model, brief fine-tuning with random unpairing reduces the gap. A reversed curriculum that places the same number of unpairing epochs at the start of training leaves a large gap. This shows that pairing dependence is shaped by the order of training and not only by the amount of unpaired training.

Cheng Wan, Chenjun Li, Qingyu Zhao

Cornell University · Weill Cornell Medicine

In-Context Learning Curriculum Learning

Oct 6, 2026cs.LG

Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers

Autoregressive Large Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and long division. In this paper, we investigate the mechanics of multi-step arithmetic in compact "Tiny" Transformers (~10.6M non-embedding parameters, 49.3M total) trained on synthetic data across four basic operations (+, -, *, /) unrolled as step-by-step scratchpads. First, we establish the necessary training foundations: (1) dataloader sequence padding creates an 83% gradient starvation artifact that collapses accuracy from 40% to 1%, remediated via continuous sequence packing; (2) linguistic pretraining is an essential prerequisite (<= 2.0% without it); and (3) modern architectural primitives (RoPE, RMSNorm, SwiGLU) and Sparse Mixture of Experts (MoE) substantially improve additive reasoning over baseline GPT-2. Second, we demonstrate that algorithmic scratchpad formulation directly dictates success. Introducing a deterministic Digit-by-Digit Long Division scratchpad within a 4-stage Hierarchical Developmental Curriculum dramatically elevates single-digit division from 4.0% to 86.7% accuracy on a 4,000-problem held-out benchmark. In contrast, multi-digit multiplication remained challenging: detailed error analysis revealed that while the model correctly computed single-digit sub-products and place-value zeros, our FOIL scratchpad failed because it forced a simultaneous summation of up to nine multi-digit terms in a single step without pairwise intermediate accumulation. Finally, we identify two key boundaries: performance collapses to 0.00% on unseen 4-digit operands, and unbuffered training induces catastrophic forgetting, collapsing division accuracy from 86.7% down to 0.00%.

Sourabh Kasliwal

Numerical Reasoning in Language Models Neural Algorithmic Reasoning LLM Training Curriculum Learning

Oct 1, 2026cs.AI

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

Automated harness optimization can substantially improve LLM agents by iteratively updating their prompts, tool interfaces, and control logic from execution feedback. However, existing methods primarily optimize how the harness is updated while largely fixing which training scenarios generate the feedback that drives those updates. As the harness evolves, the scenarios most useful for further optimization can change, suggesting that the training curriculum itself should adapt alongside the harness. We formulate this missing dimension of harness optimization as an automated curriculum learning problem and introduce ActiveSaddler. ActiveSaddler models the evolving curriculum as a non-stationary bandit with dynamically instantiated optimization targets. It abstracts recurring failures into reusable failure-pattern arms, estimates the potential learning progress from further targeting each pattern, and adaptively balances revisiting known weaknesses with exploring unseen scenarios for new ones. Optimization outcomes continually update both the set of discovered failure patterns and their priorities, allowing the curriculum to co-evolve with the harness. Experiments on GAIA2 and Terminal-Bench 2.0 show that ActiveSaddler consistently discovers stronger harnesses, improving test Pass@1 by 4.4 and 7.5 percentage points over the same harness optimizer using a scenario order fixed before optimization, respectively. Ablations further show that these gains depend on dynamically constructing optimization targets, estimating their evolving utility, and balancing continued optimization with new failure discovery. Together, these results establish automated curriculum learning as a new crucial optimization dimension for harness optimization.

Sungho Park, Wonjoong Kim, Jue Zhang +8

POSTECH · KAIST · Microsoft

Agent Harness Optimization Curriculum Learning LLM Agent Harnesses

Sep 30, 2026cs.LG

Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining

Continued pretraining enables language models to adapt to new domains and knowledge, but often at the cost of forgetting previously acquired capabilities. Replay can mitigate this trade-off, but fixed replay mixtures allocate training independently of the model's actual retention needs. We introduce Replay on Demand (RoD), which instead derives the replay allocation from the model's learning dynamics. RoD jointly prioritizes adaptation samples by their remaining learning potential and replay samples by their observed forgetting. Their competition for a shared training budget yields an online curriculum that determines what to train on at each step. Across models, scales, and adaptation domains, RoD reaches or improves upon the adaptation-forgetting frontier of tuned fixed-replay baselines and model merging without prescribing a replay allocation in advance. Replay concentrates on sources that are more vulnerable to forgetting and dynamically increases and redistributes as forgetting emerges during training. Together, our results show that replay can be allocated online from the model's evolving state, targeting what is needed, when it is needed.

Lukas Thede, Shengzhuang Chen, Stefan Winzeck +3

University of Tübingen, Tübingen AI Center · Helmholtz Munich · Munich Center for Machine Learning (MCML) +3

Continual Learning for LLMs Replay-Based Continual Learning Continued Pretraining Curriculum Learning Catastrophic Forgetting

Sep 30, 2026cs.CV

Less Data, Better Timing: Student-Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding

On-policy distillation (OPD) provides dense supervision directly on student-generated trajectories, making it an effective post-training strategy for vision-language models in temporal video grounding (TVG). However, existing pipelines typically construct the training curriculum from a fixed teacher and the initial student state, implicitly assuming that selected examples retain positive supervision value throughout optimization. We show that supervision trustworthiness and supervision necessity are distinct yet coupled: the former concerns target credibility, while the latter varies with the student's current task competence; together, they shape supervision value. Building on this coupled view, we introduce Student-Curriculum Coupling (SCC), a closed-loop framework in which a compact Anchor-Frontier curriculum defines the candidate supervision space and the evolving student dynamically determines its active subset. Supervision can therefore be activated, suspended, or reactivated as competence changes, concentrating teacher computation and optimization on current task-level deficits. Across three TVG benchmarks, SCC achieves a 5.1% relative improvement in mean recall over Video-OPD on its original curriculum, while using 60.0% fewer training examples and reducing training time by 50.4%. Ablations support the complementary roles of capability-structured curriculum design and student-dependent supervision in achieving these gains. Together, these results establish SCC as a data- and compute-efficient framework for TVG post-training, delivering stronger temporal grounding by aligning trustworthy supervision with the student's evolving learning needs.

Jiacheng Qiu, Yunsoo Kim, Ruichen Xu +3

State University of New York at Stony Brook

Temporal Video Grounding VLM Distillation Curriculum Learning On-Policy Distillation

Sep 29, 2026cs.RO

Predictive Safety Curricula for Robust Legged Locomotion

Rare but consequential failures can persist in learned locomotion policies for legged robots even when average task performance is high, in part because standard curricula primarily adapt task difficulty rather than the distribution of safety-critical experience. We introduce Predictive Safety Curricula (PSC), a framework for allocating locomotion training experience using learned predictions of future safety cost. PSC trains a distributional safety critic from policy rollouts and uses its predictions to prioritize both terrain contexts and previously encountered randomized events. The resulting curriculum modifies the training distribution while leaving the task reward and policy-optimization loss unchanged. We evaluate PSC in controlled rough-terrain locomotion and in production locomotion systems. PSC improves reliability relative to standard terrain progression, advantage-based replay, and learning-progress curricula, with the largest gains on difficult terrain and under degraded observations. The same allocation principle transfers to two production locomotion stacks. On ANYmal-D hardware, PSC reduces shank-collision incidence by

63\%

relative to the learning-progress curriculum across three matched training seeds, with a reduction in every seed. On a production stair-climbing platform, PSC eliminates observed shank collisions in the evaluated hardware trials. These results show that learned predictions of future safety cost can provide an effective signal for allocating training experience toward rare failure modes and improving locomotion reliability.

Ivan Ovinnikov, Pascal Sutter, Christian Gehring +1

ANYbotics AG Zürich, Switzerland

Curriculum RL Robot Safety Terrain-Aware Robot Locomotion RL for Legged Locomotion Curriculum Learning Robust RL

Sep 27, 2026cs.LG

Towards Eliminating Catastrophic Forgetting in the Curriculum Learning of Math Reasoning Tasks

Curriculum learning has found broad application across numerous domains. Nevertheless, its effectiveness is intrinsically curtailed by catastrophic forgetting, driven by the shifts in model parameter distributions between curriculum tasks. In this paper, we investigate the phenomenon of catastrophic forgetting in this training paradigm, building on the established efficacy of curriculum learning. Our theoretical analyses of parameter update dynamics demonstrate that catastrophic forgetting in curriculum learning stems from the divergence of task optima, which is generally essential to the faster convergence of curriculum learning; therefore, forgetting cannot be completely eliminated. Based on this finding, we augment the training process and propose IV-EWC, which incorporates Elastic Weight Consolidation (EWC) into the curriculum learning objective to curb catastrophic forgetting in mathematical reasoning, a prototypical curriculum learning scenario. IV-EWC employs the influence function to construct a representative validation set from the curriculum's training data, which is used to drive dynamic regularization during training. We further present an extended theoretical analysis to show that EWC-based regularization methods mitigate catastrophic forgetting in curriculum learning, thereby providing theoretical support for IV-EWC. Empirical evaluations on three backbone models and three benchmarks indicate that curriculum learning exhibits catastrophic forgetting. IV-EWC alleviates this issue, reducing forgetting by 162% on average relative to vanilla curriculum learning and yielding positive backward transfer, as evidenced by improved performance on easier tasks after subsequent training on challenging tasks.

Zengyan Yang, Yangyang Wu, Kai Huang +3

Zhejiang University · Ant Group

Elastic Weight Consolidation Mathematical Reasoning Curriculum Learning Catastrophic Forgetting

Sep 27, 2026cs.AI

Not Too Hard, Not Too Easy: Learning from Intermediate States for LLM Structured Reasoning

A common principle of effective learning is to practice material that is neither already mastered nor too difficult to permit progress. We ask how to apply this principle to structured reasoning tasks such as Sudoku and maze solving. In these tasks, a model can repeatedly revise an incomplete or incorrect candidate solution until it satisfies the problem's constraints. The intermediate candidate solutions along this trajectory provide natural training examples: some are already solved, some cannot yet be repaired by the model, and others lie at its current frontier of achievable progress. We therefore investigate whether pretrained language models can learn to revise such states and whether training on states at this frontier improves reasoning more broadly. To achieve this, we couple a pretrained language-model backbone with a recurrent updater that repeatedly revises an explicit solution state, using the same parameters at every update step. We further introduce Frontier-Oriented Curation Using Self-trajectories (FOCUS), which selects training states from trajectories generated by the current model. FOCUS measures how much the model improves each state within a fixed number of recurrent updates and prioritizes states from which it can make substantial progress. With Qwen3-1.7B, FOCUS achieves 64.4% exact solve accuracy on Sudoku-Extreme and 91.1% on Maze-Hard, with similar gains observed across five Qwen and Llama backbones spanning 1.7B to 8B parameters. We further observe zero-shot transfer in the adapted LLM to mathematical reasoning and code execution, even when the recurrent updater is disabled and no downstream fine-tuning is performed.

Hongbo Chen, Guohua Lu, Ting Dang +1

University of Auckland, Auckland, New Zealand · University of Melbourne, Melbourne, Australia

Self-Training for Language Models Structured Reasoning Curriculum Learning Constraint Satisfaction Large Reasoning Models

Sep 22, 2026cs.CL

Rethinking Length-Based Training: Batch Composition and Loss Normalization in Speech Token Language Models

Short-to-long training is a simple curriculum for speech models, but its gains can be difficult to interpret. In speech token language models, length-based training can change the shuffle policy, batch composition, token retention, and token weights under batch-mean loss. We disentangle these factors through matched comparisons. In the tested settings, short-to-long ordering shows no independent benefit when batch composition and token exposure are fixed. First-epoch grouping lowers perplexity for Mimi under batch-mean loss, but this gain is not observed under token-balanced loss. The cross-tokenizer results are consistent with a link between chunk-length variation and token weighting. This work provides a systematic analysis protocol for studying length-based training in variable-length speech models.

Hongjin Song, Runwu Shi, Weiqiao Shan +4

Beijing Institute of Technology, Zhuhai · Institute of Science Tokyo · Northeastern University +3

Curriculum Learning Speech Language Models

Sep 22, 2026cs.AI

Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces

Large language models (LLMs) excel at reasoning when scaled to hundreds of billions of parameters, but small- and mid-scale models remain brittle reasoners even with knowledge distillation (KD). We present Ladders-of-Thought (LoT), a framework that improves reasoning by combining progressive question rewrites with a self-evolving curriculum. LoT automatically generates semantically faithful but easier variants of reasoning problems, organizes them into difficulty buckets using step-based measures, and employs a self-evolving bandit scheduler to allocate training adaptively. Evaluated on two reasoning domains, math and multi-hop reasoning, across 1-8B models from different families, LoT consistently improves over KD. It delivers large gains on arithmetic tasks (e.g., +32 percentage points on AddSub, +25pp on SVAMP), +2-8pp improvements on in-domain test splits, and strong though dataset-dependent benefits on multi-hop reasoning (e.g., +16pp on QASC, +25pp on StrategyQA). LoT also converges faster than staged curricula, highlighting the value of adaptive progression. These results show that progressive rewrites coupled with adaptive curricula provide a simple yet effective recipe for strengthening reasoning in smaller LLMs.

Minghui Liu, Thomas Magelinski, Dehao Yuan +2

University of Maryland, College Park · Capital One

Numerical Reasoning in Language Models Curriculum Learning Multi-Hop Reasoning LLM Reasoning

Sep 21, 2026cs.NE

DCL-GPGLS: Dynamic Curriculum Learning for Genetic Programming Guided Local Search in Large-Scale Vehicle Routing

Genetic Programming Guided Local Search (GPGLS) uses genetic programming to evolve utility functions for guided local search in large-scale vehicle routing problems (LSVRPs). Evaluating every GP individual on every training instance at every generation is expensive, so GPGLS is usually trained on small instance batches. Existing curriculum-based GPGLS orders these batches mainly by instance size. Adaptive Curriculum Learning GPGLS (ACL-GPGLS) improves training efficiency by adapting when the search moves between fixed curriculum stages, but the instance difficulty order remains predefined. We propose DCL-GPGLS, which estimates the difficulty of each training instance from the current population's solution quality and updates the estimates during evolution. Each generation then receives a batch near a scheduled difficulty level, with a correction that limits repeated selection of the same instances. Experiments on a fixed training-test split of the CVRPLIB X set show that DCL-GPGLS achieves the best observed average rank and mean test cost among six training policies. It obtains the lowest mean cost on 36 of 65 unseen test instances and is significantly better than the static feedback-derived curriculum, matched in total evaluator calls, on 6 instances, with no significant difference on the remaining 59.

Saining Liu, Yi Mei, Mengjie Zhang

School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand

Metaheuristic Optimization Genetic Programming Vehicle Routing Curriculum Learning

Sep 17, 2026cs.LG

Learn Your Own Thoughts: Abstract Token Curriculum

Large Language Models (LLMs) have achieved remarkable reasoning capabilities by utilizing chain-of-thought (CoT) as a scratchpad for intermediate stages of thinking. However, CoT techniques require explicit supervision on thinking tokens, which requires rich, task-specific data. In this work, we propose Abstract Token Curriculum (ATC), a novel curriculum learning framework that elicits effective continuous intermediate representations without direct supervision or manual scratchpad design. ATC gradually increases problem complexity through a sequence of distributions, training the model to develop internal abstract

thoughts'' in the continuous representation space. This paper provides both theoretical and experimental evidence for the benefits of ATC and its advantages over previous methods for training continuous thoughts. Theoretically, we show that for learning parity functions with single-layer softmax attention using ATC, attention naturally focuses on the CoT tokens in the context that provide the

easiest path'' to predicting the next token. Experimentally, we show ATC's effectiveness on graph reachability and arithmetic learning tasks.

Khashayar Gatmiry, Avrajit Ghosh, Parsa Mirtaheri +4

UC San Diego · Google DeepMind and UC Berkeley

CoT Reasoning Curriculum Learning LLM Training Latent Reasoning

Sep 16, 2026cs.CL

STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution

Large language models (LLMs) often suffer from capability stagnation in self-improvement training because fixed difficulty levels fail to adapt to their evolving proficiency. To address this issue, we propose STRETCH (Self-Taught Reasoning Evolution via Targeted CHallenge), a unified framework inspired by cognitive scaffolding theory. STRETCH introduces a dynamic Stretch Zone mechanism that continuously aligns question difficulty with the model's solving capability. Within a single parameter space, the model alternates between a Scaffolder that generates adaptive, boundary-pushing challenges and a Learner that that optimizes its solving trajectories through reinforcement learning. This dual-loop co-evolution effectively stabilizes training, mitigates reward hacking and promote progressive reasoning growth. Experiments on both negotiation and operation research benchmarks demonstrate that STRETCH consistently outperforms strong prompting and domain-specific baselines. Further scaffolder configuration analysis shows that dynamic difficulty alignment is critical for sustained capability improvement and synchronized reasoning evolution.

Yajie Yu, Mark Lee, Yue Feng

School of Computer Science University of Birmingham Birmingham United Kingdom

Self-Training for Language Models RL for Language Model Reasoning Curriculum Learning Language Model Self-Improvement

Sep 16, 2026cs.LG

Layer-wise Curriculum Learning for Efficient LLM Compression

In this paper, we introduce layer-wise curriculum learning for efficient LLM compression. The proposed method facilitates the knowledge transfer from the teacher model to the student model, utilizing a curriculum learning approach that begins with easier optimization tasks and progressively tackles harder ones. In order to adopt the layer-wise learning in LLM compression, we partition the whole model into multiple segments consisting of layers, thereby enabling more computationally efficient knowledge transfer for LLMs. Based on our theoretical analysis of cumulative error phenomenon, layer-wise curriculum learning accelerates convergence while stabilizing the knowledge transfer process. In addition, we present a feature caching method with a multi-threading strategy to efficiently address feature misalignment across layers, maximizing GPU utilization. Consequently, our method exhibits advanced model compression performance, as well as high computational efficiency in terms of minimized memory usage and short training hours. Experiments on multiple datasets show that the proposed method achieves state-of-the-art performance while reducing GPU memory usage and training hours by more than 50% on BERT and GPT-2. Moreover, it outperforms the other pruning methods on LLaMA-family and Qwen models under the same training hours, with a lower GPU memory footprint.

Donggeon Lee, Dooyeon Na, Seungmin Oh +1

Ajou University, South Korea

LLM Compression Curriculum Learning Knowledge Distillation Memory-Efficient Training

Sep 14, 2026cs.LG

Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It

Fixed-state recurrences--linear attention and state-space models--are reported to lag behind attention on associative recall, but whole-architecture comparisons cannot say which ingredient is responsible. We decompose masked multi-query recall at a fixed state budget along three single-knob axes: a short causal convolution, the transition structure (rank-1 delta rule vs. diagonal), and decay. The convolution dominates (~+0.5 recall in both families under matched training): comparisons that pit convolution-free cells against a convolution-equipped Mamba measure the missing convolution, not the recurrence. The rank-1 transition beats its diagonal ablation by +0.19/+0.32 at 16/32 pairs, but the margin shrinks to +0.03 once both cells carry the convolution, and a state-matched Mamba-2 ties the unarmed rank-1 cell: no class claim survives. Cells that solve 32-pair recall degrade gracefully with load yet fall to chance retrieving 4 pairs from a distractor haystack--flat across lengths and transitions. Interference under sparse supervision, not capacity: a distance curriculum takes the unchanged architecture from 0.021 to 1.000. Training is a lock-in lottery--a seed either locks in or does not--and the curriculum is the lever. Lock-in rises from 1/10 to 7/10 (p=0.02); dense supervision adds nothing; at L=256 a shaped ramp reopens a boundary the uniform curriculum cannot (4/5 vs. 0/9); and at L=512, where the ramp collapses (0/6), gating it on measured accuracy locks in 6/6 (p=0.001). Bidirectional denoiser cells, reading the query before the haystack, show no measurable advantage over causal training (ten seeds), and collision-key retrieval needs two layers. Arming for recall is free on an S_5 state-tracking guardrail--the armed cell is significantly better at every depth (p<=0.0044). These replace "recurrent models are bad at recall" with a measured decomposition and two cheap interventions.

Julian Boesch, Andrew Wee

1Purdue University · 2Obit Research

Recurrent Neural Networks Curriculum Learning Associative Memory State Space Models

Sep 9, 2026cs.CV

BrainTaskonomy: Learning How to Pretrain and What to Transfer in fMRI Foundation Models

fMRI foundation models increasingly aggregate heterogeneous data across brain states, cohorts, and acquisition settings, yet pretraining domains are commonly treated as a flat mixture and downstream tasks are adapted independently. We study whether measured learning relations can organize both stages without modifying the backbone. During pretraining, a lightweight Brain-DiT proxy estimates difficulty and directed facilitation across ten fMRI domains, yielding a priority-guided cumulative domain curriculum combined with high-to-low-noise timestep scheduling and joint consolidation. During adaptation, controlled first- and higher-order transfer across fifteen tasks constructs a directed taskonomy, from which budgeted integer programming (BIP) selects directly supervised source tasks and target-specific routes. The joint priority-domain and high-to-low-timestep curriculum reduces v-NMSE, PSD-NMSE, and FC-MSE by 6.5%, 16.3%, and 10.5%, respectively, relative to uniform sampling over both dimensions, and shows strong downstream performance across six in- and out-of-domain tasks. The taskonomy reveals asymmetric, target-dependent transfer, while exploratory sealed-test evaluation shows larger descriptive gains for BIP policies when higher-order route spaces are available than for matched random controls. Together, these findings support organizing fMRI pretraining and adaptation by measured learning relations rather than treating domains and tasks as independent flat sets.

Junfeng Xia, Wenhao Ye, Junxiang Zhang +3

Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, China · Department of Computer Science, University of Warwick, The UK · Omni-Intelligence, Shenzhen, China +1

Medical Imaging Foundation Models fMRI Foundation Models Task Transferability Estimation Transfer Learning Curriculum Learning

Sep 8, 2026cs.LG

Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics

Curriculum learning is governed by several coupled design choices---how difficulty is defined, how examples are ordered, how much exposure each level receives, and how quickly training moves across levels---making it hard to isolate what actually helps. We present Wasserstein curriculum paths, a simple transport-based framework that decouples these factors by representing curricula as trajectories of training distributions over discrete difficulty levels. Across a calibrated synthetic suite with 12 tasks and 33 difficulty axes, we use this framework to isolate the effects of ordering, matched exposure, endpoint smoothness, and pacing under fixed training budgets. We find that curriculum effects are strongly context-dependent: no single strategy dominates across tasks, difficulty axes, and budgets, and curricula mainly change where a fixed budget is spent most effectively. Within this framework, easy-to-hard ordering improves hard-level performance relative to exposure-matched static sampling, showing that the benefit is not explained by cumulative exposure alone. We further show that endpoint smoothness and pacing substantially affect where along the difficulty spectrum a curriculum is effective. Finally, we show that the same transport view naturally supports extensions to learned pacing through geometry and to structured difficulty spaces beyond one-dimensional orderings.

Changho Shin, David Alvarez-Melis

Princeton University · Microsoft Research & Harvard University

Curriculum Learning

Aug 31, 2026cs.CV

Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum

Despite the impressive progress of recent MLLMs on spatio-temporal video grounding (STVG), existing evaluations and training data focus primarily on simple queries. They largely overlook the compositional queries prevalent in real-world scenarios, where a target must be disambiguated by jointly reasoning about its attributes and relations to other entities. To bridge this gap, we propose Compositional Spatio-Temporal Video Grounding (CompSTVG), a task that requires models to process complex textual queries where every intertwined attribute and relational cue is essential for disambiguation. To facilitate this task at scale, we build a synthetic data engine that leverages a spatio-temporal scene graph as a difficulty measure and casts difficulty-controlled query synthesis as a constraint programming problem, producing difficulty-graded data for both evaluation and training. Built on this engine, we introduce STVG-CompBench, a benchmark stratified by explicit difficulty levels that jointly capture temporal complexity and spatial interference. Evaluating 11 representative STVG models on STVG-CompBench reveals that current models perform poorly on compositional queries, exhibiting a sharp performance drop that is typically obscured by overall dataset-level averages. We further construct synthetic training data and propose CurrSTVG, a curriculum reinforcement learning framework that delivers consistent gains, with the largest improvements observed on the most challenging compositional queries.

Xingjian Wang, Shijian Wang, Yibo Wang +4

1Monash University · 2Southeast University · 3Shanghai University of Electric Power

Temporal Video Grounding Synthetic Data Generation Vision-Language Grounding Curriculum Learning

Aug 22, 2026cs.CV

Three-Phase Scribble-Adaptive Curriculum Learning for autoPETV Grand Challenge

This report describes Libo Zhang's algorithmic solution to autoPETV Grand Challenge on interactive lesion segmentation in whole-body PET/CT. Interaction is encoded as two additional input channels that rasterize the accumulated foreground and background scribbles, and a residual-encoder U-Net of about 140 million parameters is trained with a three-phase curriculum over 4000 epochs: the network first learns fully automatic segmentation with silent interaction channels, then observes ground-truth-derived scribbles under randomly sampled visibility modes, and finally adapts to its own mistakes through online simulation of up to five error-driven correction steps. Training draws on 1811 autoPET and DeepPSMA studies, and the submission ensembles the best and final checkpoints of five folds by logit averaging. In interactive five-fold cross-validation with six interaction steps, the final checkpoints reach a mean AUC-Dice of 3.836 and a mean AUC-DMM of 3.869, improving monotonically in every fold, with roughly half of the total gain delivered by the first corrective scribble. Our code and trained model checkpoints are available on https://github.com/Libo1023/autoPETV-Curriculum.

Libo Zhang, Yue Ning

Duke University

Interactive Medical Image Segmentation Medical Image Segmentation Curriculum Learning PET/CT Tumor Segmentation

Aug 13, 2026cs.LG

Into the ORBIT for Time Series: Training Regimes for Foundation Models

Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored. As a result, pre-training distributions are often poorly controlled with respect to domain imbalance, context requirements, prediction horizons, and missingness. We introduce ORBIT (Omni-Range Bootstrap Incremental Training), a training paradigm that makes this distribution explicit and controllable. ORBIT combines Bootstrap Multi-Level Sampling, which controls dataset exposure and samples records, target variables, context windows, and prediction horizons, with Omni-Range Incremental Training, which varies context lengths and prediction horizons throughout a single training stage. Under ORBIT, we train Falcon-2.0, a simple univariate encoder-only Transformer with missingness-aware triple-channel patch tokenization and parallel patch prediction. We further introduce Rank-Guided Cross-Depth Alignment, a training objective that uses late-layer representations as stop-gradient teachers for shallow layers without additional inference cost. Evaluations on GIFT-Eval and fev-bench demonstrate strong zero-shot forecasting performance across diverse domains and frequencies.

Hongjie Xia, Yiding Liu, Yifan Hu +2

Zero-Shot Time Series Forecasting Self-Supervised Pre-Training Curriculum Learning Time-Series Foundation Models

Aug 11, 2026cs.CR

Cross-Corpus Evaluation of Generalizable Vulnerability Detection in IoT Firmware

IoT firmware vulnerability detection remains challenging due to heterogeneous firmware ecosystems, resource-constrained platforms, and limitations in existing benchmarks. Many datasets are synthetic or general-purpose and lack human-verified, contamination-screened annotations, limiting evidence on cross-corpus generalization across training sources, model architectures, and curriculum strategies. To address this gap, this paper introduces IoTVulBench, a human-verified benchmark for cross-corpus firmware vulnerability detection. IoTVulBench-Core was constructed from GitHub repositories, validated by three expert reviewers, and evaluated on a contamination-screened held-out target across five model architectures, two tuning methods, and three curriculum strategies, with ensemble, distillation, and robustness analyses. Models trained on IoTVulBench achieved the highest MCC among matched single-source datasets, reaching 0.58 versus 0.44 for PrimeVul and 0.39 for D2A. Staged curriculum learning increased MCC to 0.69, while a diversity-optimized ensemble achieved 0.73, improving by 0.42 MCC over the strongest reference comparator, a static analyzer at 0.31, and by 0.29 over PrimeVul. At a 0.5% false-positive rate, the model missed only 21% of vulnerabilities, compared with 71% for the strongest comparator. It retained 86% of its performance under identifier renaming and demonstrated strong calibration and largely faithful explanations. These findings indicate that domain-matched training data and curriculum design, rather than model scale alone, are key drivers of generalization in firmware vulnerability detection. The results provide a benchmark for future research and deployment-ready configurations for practical IoT security applications.

Sadib Hassan Rumman, Md. Shariful Islam, Md. Rayhanur Rahman

Institute of Information Technology University of Dhaka Dhaka, Bangladesh · Department of Computer Science The University of Alabama Tuscaloosa, AL, USA

Software Vulnerability Detection Curriculum Learning

Aug 11, 2026cs.CL

Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue

Large language models have demonstrated conversational capabilities, yet empathetic competence remains challenging. Empathetic support is inherently multi-turn and path-dependent: users disclose concerns gradually, emotions evolve over time, and early responses shape trust and receptivity. Reinforcement learning with verifiable emotion rewards provides scalable supervision for long-horizon interactions. However, existing methods evolve the dialogue policy while keeping its training interaction distribution fixed, creating a mismatch between policy competence and training experience. We introduce a dual-loop self-evolution framework driven by verifiable emotion feedback. With the user simulator and verifier frozen, the inner loop optimizes the multi-turn policy using continuous emotion rewards, while the outer loop uses the same outcomes to estimate policy-relative interaction utility and adapt experience. To obtain estimates from sparse, stochastic rollouts, the framework holds the scenario and interaction state constant within each group and prioritizes conditions whose group pass rates lie near the policy's competence boundary. A hierarchical controller shares evidence across support intents, while uncertainty-guided exploration and uniform rehearsal prevent premature exclusion. The resulting distribution generates trajectories, closing both loops without increasing the rollout budget. On SAGE, our framework raises Qwen3-8B Overall from 53.87 to 79.24 and outperforms protocol-matched uniform emotion-reward reinforcement learning by 7.23 points.

Yi Wei, Shuo Jiang, Huaixia Dou +5

Qwen DianJin Team, Alibaba Cloud Computing · Beihang University · School of Computer Science and Technology, Soochow University

Reinforcement Learning with Verifiable Rewards Curriculum Learning Language Model Self-Improvement Emotion-Aware Dialogue Generation

Aug 10, 2026cs.RO

Predictive safety filter enhanced curriculum learning control for efficient vehicle dynamics controller

Recent advances in learning-based control have enabled impressive achievements in solving complex control problems in various domains. However, since learning-based control may not be able to realize safety-guaranties, it is of great importance to enhance safety and robustness while maintaining good performances. Take vehicle motion & dynamics control as an example, in order to overcome the pain points of traditional methods such as heavy parameter calibration effort and learning-based control to bring better performance and efficiency in stability & agility over prior work for state-based vehicle control tasks, in this work, our method aims to develop a curriculum learning controller enhanced with physics-based predictive safety filter. The validation is conducted with the Python-CarSim platform, demonstrating better improvements and scalability under various maneuvers.

Baocong Zhang, Siliang Lu, Chenyang Li

1Shanghai Jiaotong University, Shanghai, China · 2Bosch Corporate Research, Shanghai, China

Safety-Critical Control Vehicle Dynamics Curriculum Learning

Aug 5, 2026cs.AI

Stochasticity Is Not the Hard Part: Reduction and Complexity in Instructional Sequencing over Prerequisite DAGs

When a student must learn concepts connected by prerequisite dependencies, when does the order of instruction matter, and what does it cost to find the best one? We study instructional sequencing as a stochastic shortest-path problem in which attempting a concept succeeds with a state-dependent probability and failure leaves the learner state unchanged. We first prove that this stochasticity can be eliminated exactly: the problem collapses to a deterministic shortest-path problem on the lattice of prerequisite order ideals, preserving optimal values and actions. The collapse removes stochastic complexity but not combinatorial complexity: optimal sequencing remains NP-hard -- via reduction from feedback arc set in tournaments -- even with no prerequisite edges, unit costs, uniform binary nonnegative transfer, and success probabilities at least

1/2

. Hardness is not uniform: when realizable transfer preferences remain jointly acyclic with the prerequisites, any topological order of the residual joint graph is optimal, and fixed prerequisite width yields polynomial-time exact dynamic programming. A computable diagnostic,

mΔ

, bounds the value of sequencing before optimization. On 70,893 interactions from an introductory CS course, the diagnostic certifies a doubly easy regime -- little value to optimize and little space to search -- while constructed transfer instances realize the challenging regime, where myopic sequencing suffers large regret yet exact A* with a consistent heuristic expands only linearly many states on that family.

Zonglin Han, Yichen Chen, Jiawen Jiang +2

Department of Computer Science, University of California, Davis · International Digital Economy College, Minjiang University · 2International Digital Economy College, Minjiang University +1

Markov Decision Processes Educational Technology Combinatorial Optimization Curriculum Learning

Aug 4, 2026cs.CV

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

Recent works train agents by constructing large-scale multimodal environment pools. However, we find that simply increasing the number of multimodal environments does not always benefit. We further analyze the limitations in current multimodal environment distributions through a series of experiments. Based on these findings, we study how to build more effective training environment distributions from two dimensions: diversity and difficulty structure. For diversity, we propose Ability-aware Environment Selection (AES) to obtain diverse environment sets. For difficulty structure, we propose Hierarchical Difficulty Curriculum (HDC), which organizes curriculum learning through two difficulty levels: harness weakening and state-scale progression. Experiments show that AES and HDC effectively improve multimodal agent training.

Kejian Zhu, Zhuoran Jin, Dongqi Huang +4

The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

Curriculum Learning Multimodal Agents

Aug 3, 2026cs.CV

CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning

Chart question answering (CQA) requires multimodal large language models (MLLMs) to integrate visual comprehension with logical reasoning, yet current models struggle with accurate visual grounding and coherent reasoning chains. While extrinsic chain-of-thought prompting and visual cues significantly improve performance, current MLLMs lack intrinsic visual grounded reasoning capabilities, leading to inaccurate perception and reasoning disconnected from visual evidence. To address these limitations, we propose CURV, a curriculum learning framework that develops intrinsic visual reasoning capabilities by reformulating CQA as multi-step visual grounded reasoning, where each step coordinates logical reasoning with dynamic visual grounding through spatial attention concentration. To assist model learning, we further introduce CCQA, a three-level curriculum dataset with scalable synthetic generation across diverse chart types and reasoning patterns. Our curriculum systematically progresses from basic single-operation reasoning to complex multi-chart compositional tasks. Experiments demonstrate that CURV achieves up to

\uparrow20.50\%

improvements over baselines and is generalizable to real-world benchmarks (up to

\uparrow12.30\%

) and out-of-domain multimodal reasoning tasks (up to

\uparrow10.20\%

), validating the effectiveness of internalizing visual reasoning with dynamic grounding for enhanced chart understanding capabilities. Code is available at: https://xhguo7.github.io/CURV/.

Xuehang Guo, Pingyue Zhang, Ruiyi Zhang +6

1William & Mary · 2Northwestern University · 3Adobe +1

Data Visualization Chart QA Multimodal CoT Reasoning Visually Grounded Reasoning Curriculum Learning

Aug 1, 2026cs.RO

Staged Multi-Agent Training (SMAT) for Hip Exoskeletons: Metabolic and Biomechanical Validation of a Simulation-Trained Co-Adaptive Controller

Learning-based controllers can deliver exoskeleton assistance after training entirely in physics-based simulation, yet few controllers that address human-device co-adaptation have been validated on real users by whole-body metabolic measurement, the standard benchmark for assistive walking. Co-adaptation is challenging: as the device alters joint dynamics, the wearer reorganizes neuromuscular coordination, producing a non-stationary learning problem. Staged Multi-Agent Training (SMAT), a four-stage curriculum that progressively trains a musculoskeletal human actor and a bilateral hip exoskeleton actor, was introduced and shown to reduce simulated hip-muscle activation and provide positive assistance on hardware. This article provides the first physiological validation of SMAT. The policy was deployed on a hip exoskeleton and tested with eight healthy adults, with metabolic cost measured by indirect calorimetry across no-exoskeleton, passive, and active conditions. Active assistance lowered net metabolic rate by 19.7% relative to the passive device (p < 0.001). Biomechanical analysis confirmed predominantly positive hip mechanical power across all subjects (positive-power ratio 0.98), and the policy generalized across walking speeds and terrains. Together, these results show that a single simulation-trained SMAT policy, deployed without subject-specific retraining, delivers a significant metabolic benefit on real users while remaining robust beyond the conditions it was trained on.

Yifei Yuan, Jakob Wolf, Ghaith Androwis +1

Department of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ 07102, USA · Kessler Foundation, West Orange, NJ 07052, USA

Robotic Control Assistive Robotics Curriculum Learning Cooperative MARL

Aug 1, 2026cs.AI

Evolutionary Curriculum Learning Improves Biological Sequence Modeling

Variational autoencoders (VAEs) trained on multiple sequence alignments (MSAs) have emerged as powerful generative models for biological sequences, with applications ranging from disease variant prediction to functional RNA design. However, standard biological VAE training treats all sequences as exchangeable, ignoring the rich evolutionary structure that organizes homologous sequences from evolutionarily close to highly divergent. We propose Evolutionary Curriculum Learning (ECL), a training strategy that exploits this structure by progressively exposing the model to sequences of increasing evolutionary distance from sampled anchors, following a power-law expansion schedule. Applied to two architecturally distinct VAE models and two biological domains--protein variant effect prediction with EVE and RNA family sequence generation with RfamGen--ECL improves downstream task performance across five random seeds per configuration. Mean ClinVar classification AUROC rises from 0.981 to 0.989 for p53; for PTEN, ECL attains 1.000 in every seed whereas the baseline is unstable (mean 0.905, falling as low as 0.54). For RNA, ECL raises mean covariance-model bit scores on all three families tested and exceeds its seed-matched baseline in 12 of 15 training runs, though with only three families the effect cannot be established as significant at the family level. Ablation experiments show that progressively expanding the sampled sequences by evolutionary distance outperforms fixed-size neighborhood sampling in addition to uniform random sampling. Evolutionary distance is therefore a useful inductive bias for ordering the training curriculum in biological sequence modeling.

Richard Zhu, Kento Nishi

Department of Computer Science, Harvard University, Cambridge, MA, USA · Department of Statistics, Harvard University, Cambridge, MA, USA.

Variational Autoencoders Curriculum Learning Molecular Generation Sequence Modeling

Aug 1, 2026cs.CV

Test-Time Curriculum for Open-Set AIGC Detection

AI-generated image detectors deployed in open-world environments inevitably face distribution shifts as new and stronger generative models continue to emerge. Although existing methods improve cross-generator generalization through better representations or training data construction, they typically follow a static train-once-and-deploy paradigm and cannot adapt after deployment. In this work, we study open-set AIGC image detection from a test-time adaptation perspective. We propose Test-Time Curriculum (TTC), a simple and model-agnostic framework that adapts a detector on unlabeled test data through curriculum-based self-training. TTC starts from highly reliable pseudo-labeled samples and progressively incorporates harder yet informative cases, while enforcing class-balanced selection to reduce biased updates under generator shift. To further improve pseudo-label quality, we introduce Cross-Scale Pseudo-Label Refinement, which aggregates complementary evidence across multiple resolutions for more reliable adaptation, and applies noisy-or fusion at inference to strengthen final predictions. In addition, we construct AIGCGuard, a new benchmark containing 3,100 representative real images and 124,000 generated images from 40 of the most advanced open-source and proprietary text-to-image models. Extensive experiments on five benchmarks show that TTC substantially improves overall detection performance under diverse unseen-generator shifts, establishing a practical and effective test-time adaptation framework for open-set generated image detection.

Yiqian Zhang, Zheyuan Gu, Xiangzhao Hao +8

Hangzhou Dianzi University · ERNIE Team, Baidu Inc. · Harbin Institute of Technology (Shenzhen)

Test-Time Adaptation Curriculum Learning AI-Generated Image Detection

Jul 31, 2026cs.CV

Domain-Division based Progressive Learning for Source-Free Domain Adaptation

With growing privacy and portability concerns, source-free domain adaptation requires only a source pre-trained model and an unlabeled target domain, allowing for effective adaptation to the target data. Most existing self-training methods focus on selecting and exploiting samples with reliable predictions, often neglecting others. Inspired by the finding that deep models learn clean samples faster than noisy ones, we propose a domain-division based progressive learning method named DPL. Specifically, our approach consists of two alternating stages, each beginning with the division of the target domain into easy-to-adapt and hard-to-adapt subdomains based on adaptation difficulty, followed by neighborhood-based pseudo label assignment. In stage one, we enhance classification accuracy through uncertainty-aware self-training and alignment of corresponding classes between subdomains. Stage two then applies tailored learning strategies to each subdomain, starting with consistency learning on the easy-to-adapt samples and progressing to utilizing local structural information for the more challenging ones, thereby mining the intrinsic properties of the target data. Extensive experiments on several widely used benchmarks validate the effectiveness of our approach, demonstrating superior performance compared to state-of-the-art methods. Our code is available at https://github.com/iamjingli/DPL.

Pan Liu, Jing Li, Meng Zhao +3

School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, China

Source-Free Domain Adaptation Unsupervised Domain Adaptation Self-Training Pseudo-Labeling Curriculum Learning