Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-policy reinforcement learning can reduce forgetting, it requires explicit reward functions that are often unavailable. Learning from expert demonstrations, the primary alternative, is dominated by supervised fine-tuning (SFT), which is inherently off-policy. We introduce Self-Distillation Fine-Tuning (SDFT), a simple method that enables on-policy learning directly from demonstrations. SDFT leverages in-context learning by using a demonstration-conditioned model as its own teacher, generating on-policy training signals that preserve prior capabilities while acquiring new skills. Across skill learning and knowledge acquisition tasks, SDFT consistently outperforms SFT, achieving higher new-task accuracy while substantially reducing catastrophic forgetting. In sequential learning experiments, SDFT enables a single model to accumulate multiple skills over time without performance regression, establishing on-policy distillation as a practical path to continual learning from demonstrations.
论文检索
输入标题、作者或关键词，从 13,033 篇学术成果中精准定位
Applications · Everything Else
Execution-grounded LLM agents offer a promising paradigm for learning from tool feedback, but such feedback is often expensive and slow to obtain, making online reinforcement learning (RL) impractical. High-coverage hardware verification exemplifies this challenge due to its reliance on industrial simulators and non-differentiable execution signals. We propose LLM4Cov, an offline agent-learning framework that models verification as memoryless state transitions guided by deterministic evaluators. Building on this formulation, we introduce execution-validated data curation, policy-aware agentic data synthesis, and worst-state-prioritized sampling to enable scalable learning under execution constraints. We further curate a reality-aligned benchmark adapted from an existing verification suite through a revised evaluation protocol. Using the proposed pipeline, a compact 4B-parameter model achieves 69.2\% coverage pass rate under agentic evaluation, outperforming its teacher by 5.3\% and demonstrating competitive performance against models an order of magnitude larger.
We study program-learning methods that are efficient in both samples and computation. Classical learning theory suggests that when the target admits a short program description (for example, a short piece of ``Python code''), it can be learned from relatively few examples by performing ERM over the program class. However, this approach relies on enumerating candidate programs, which is typically exponential in the description length. In contrast, gradient-based training avoids explicit search, but for some families of short programs it can require exponentially many samples to succeed. We propose \textsc{LLM-PV}, a propose-and-verify recipe that enables ERM-style selection over a discrete program class without exhaustive enumeration. A pretrained LLM induces a proposal distribution over candidate programs; each proposal is executed, scored on a held-out validation set, and the best program is selected. The method uses no gradient updates and does not use validation feedback to adapt the sampling distribution. Across algorithmic tasks including parity variants, pattern matching, and primality testing, \textsc{LLM-PV} often recovers the exact underlying rule from a small labeled set and generalizes far beyond the training sequence lengths. In the same regimes, SGD-trained transformers and standard adaptation baselines (fine-tuning and in-context learning), as well as classical ML baselines, can fit the training data yet fail to generalize reliably. Together, these results suggest that pretrained LLM priors can serve as effective search biases for ERM, narrowing the gap between statistical and computational efficiency.
Deep Learning · Large Language Models
Training large language models (LLMs) typically relies on adaptive optimizers such as Adam, which introduce extra operations and require significant more memory to maintain first- and second-order moments than SGD. While recent works such as GaLore, Fira and APOLLO have proposed state-compressed variants to reduce memory consumption, a fundamental question remains: What are the minimum modifications to plain SGD needed to match state-of-the-art pretraining performance? We systematically investigate this question using a bottom-up approach, and identify two simple yet highly (memory- and compute-) efficient techniques: (1) column-wise gradient normalization (normalizing the gradient along the output dimension), which boosts SGD performance without momentum; and (2) applying first-order momentum only to the output layer, where gradient variance is highest. Combining these two techniques lead to SCALE (Stochastic Column-normAlized Last-layer momEntum), a simple optimizer for memory efficient pretraining. Across multiple LLaMA models (60M–1B), SCALE matches or exceeds the performance of Adam while using only 35–45% of the total memory. It also consistently outperforms memory-efficient optimizers such as GaLore, Fira and APOLLO, making it a strong candidate for large-scale pretraining under memory constraints. For LLaMA 7B model, SCALE outperforms the state-of-the-art memory-efficient methods APOLLO and Muon, in terms of both perplexity and memory consumption.
Applications · Computer Vision
Medical foundation models (MFMs) aim to learn universal representations from multimodal medical images that can generalize effectively to diverse downstream clinical tasks. However, most existing MFMs suffer from information ambiguity that blend multimodal representations in a single embedding space, leading to the degradation of modality specificity and diversity. In this paper, we propose M-IDoL, a self-supervised ***M***FM that introduces ***I***nformation ***D***ecomposition for multim***o***dal representation ***L***earning via two objectives: i) maximize inter-modality entropy by dispersing multimodal representation into separable Mixture-of-Experts (MoE) subspaces to achieve representation specificity across modalities; and ii) minimize intra-modality uncertainty by performing fine-grained semantic discrimination within each MoE subspace to enrich representation diversity per modality. By pre-training on 1.15 million medical images, M-IDoL i) delivers superior generalization across 21 downstream clinical tasks, outperforming 20 foundation models on five imaging modalities (e.g., X-ray, fundus, OCT, dermoscopy and pathology), and ii) learns modality-specific and diverse representations, showing clearer separation of feature cluster across modalities and finer-grained feature discrimination within each modality.
Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modeling dynamics, existing VAR token reduction methods face three key limitations: heuristic stage partition, non-adaptive schedules, and limited acceleration scope, thereby leaving significant acceleration potential untapped. Since entropy variation intrinsically reflects the transition of predictive uncertainty, it offers a principled measure to capture modeling dynamics evolution. Therefore, we propose NOVA, a training-free token reduction acceleration framework for VAR models via entropy analysis. NOVA adaptively determines the acceleration activation scale during inference by online identifying the inflection point of scale entropy growth. Through scale-linkage and layer-linkage ratio adjustment, NOVA dynamically computes distinct token reduction ratios for each scale and layer, pruning low-entropy tokens while reusing the cache derived from the residuals at the prior scale to accelerate inference and maintain generation quality. Extensive experiments and analyses validate NOVA as a simple yet effective training-free acceleration framework. Code is available.
Deep Learning · Generative Models and Autoencoders
Text-to-image models have advanced high-fidelity content generation, but their inability to maintain subject consistency hampers realistic applications. Existing training-based methods rely on heavy computation and large datasets; while training-free approaches demand excessive memory or complex auxiliary modules. In this paper, we first reveal a key property overlooked in prior works that the identity-relevant signals, termed Identity-Preserving Embeddings (*IPemb*), are implicitly encoded in textual embeddings of frame prompts. To address the consistent T2I generation with the *IPemb* embedding, we propose Boost Identity-Preserving Embedding (*BIPE*), a training-free yet plug-and-play framework that explicitly extracts and enhances the *IPemb*. Its core innovations are two complementary techniques: First, Adaptive Singular-Value Rescaling (*adaSVR*) applies singular-value decomposition to the joint embedding matrix of all frame prompts, amplifying identity-centric components while suppressing frame-specific noise. Second, Union Key (*UniK*) further reinforces consistency by aligning the T2I backbone’s image-text attention across the entire generation sequence. Experiments on the *ConsiStory+* benchmark demonstrate *BIPE* outperforms existing methods in both qualitative and quantitative metrics. To address the gap in evaluating a broader range of scenarios with diversified prompt templates, we introduce a *DiverStory* benchmark to further confirm our scalability.
Deep Learning · Large Language Models
Existing tasks fall short in evaluating reasoning ability of Large Language Models (LLMs) in an interactive, unknown environment. This deficiency leads to the isolated assessment of deductive, inductive, and abductive reasoning, neglecting the integrated reasoning process that is indispensable for humans discovery of real world. We introduce a novel evaluation paradigm, black-box interaction, to tackle this challenge. A black-box is defined by a hidden function that maps a specific set of inputs to outputs. LLMs are required to unravel the hidden function behind the black-box by interacting with it in given exploration turns, and reasoning over observed input-output pairs. Leveraging this idea, we build the Oracle benchmark which comprises 6 types of black-box task and 96 black-boxes. 19 modern LLMs are benchmarked. o3, a leading LLM from OpenAI, ranks first in 5 of the 6 tasks, achieving over 70\% accuracy on most easy black-boxes. But it still struggles with some hard black-box tasks, where its average performance drops below 40\%. Further analysis indicates a universal difficulty among LLMs: They lack the high-level planning capability to develop efficient and adaptive exploration strategies for hypothesis refinement.
Applications · Neuroscience, Cognitive Science
Foundation models for intracranial neural recordings aim to learn generalizable representations from large-scale unlabeled data. However, existing approaches rely on suboptimal tokenization schemes -- treating individual electrode channels as independent tokens or aggregating them into a single brain-wide representation -- which fail to capture the brain’s inherent functional modularity. We introduce NeuroCLUS, a foundation model that learns to represent neural activity through data-driven functional clusters. NeuroCLUS is built on a novel two-stage pre-training framework. First, a spatial-temporal model learns a functional context graph between channels via a functional context prediction task. Second, this graph guides a soft clustering of channels into a set of learnable prototype tokens, enabling the transformer backbone to process coherent functional units rather than raw channels. Evaluated across a diverse range of decoding paradigms -- including speech perception, speech production, and seizure detection -- NeuroCLUS consistently achieves state-of-the-art performance. The discovered functional clusters align with established neurophysiology and offer enhanced interpretability. Our work demonstrates that explicitly modeling functional neural groupings significantly improves the efficiency, generalization, and interpretability of foundation models for intracranial decoding.
Discrete Diffusion Large Language Models (dLLMs) have recently emerged as a promising non-autoregressive paradigm, offering faster inference while achieving strong performance in code generation and mathematical reasoning tasks. In this work, we show that dLLMs’ decoding mechanism not only improves utility but also enables effective model attribution: by analyzing a response’s decoding trajectory, we can identify its source model and help mitigate risks from model misuse. A key challenge is the diversity of attribution scenarios, ranging from distinguishing different models to identifying different checkpoints or backups of the same model. To ensure broad applicability, we focus on two core questions: what information to extract from the decoding trajectory, and how to use it effectively. We first observe that per-step model confidence is ineffective, as the bidirectional nature of dLLMs causes mutual influence among decoded tokens, leading to highly redundant confidence signals that obscure structural information about decoding order and dependencies. To overcome this, we propose a novel information extraction scheme called the \textit{Directed Decoding Map (DDM)}, which captures structural relationships between decoding steps and reveals model-specific behaviors. Furthermore, to fully leverage the extracted structure, we propose \textit{Gaussian-Trajectory Attribution (GTA)}, which fits a cell-wise Gaussian distribution at each decoding position for each model and uses log-likelihood differences between trajectories as the attribution score. Extensive experiments across diverse models, datasets and different model access assumptions validate the effectiveness of our approach.
Theory · Learning Theory
One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final prediction is obtained by applying a logistic link function to a linear score. In binary logistic regression, the feedback can be either soft labels, corresponding to the true conditional probability of the data (as in distillation), or sampled hard labels (taking values $\pm 1$). We point out a fundamental problem that arises even in a particularly favorable setting, where the goal is to learn a noise-free soft target of the form $\sigma(\mathbf{x}^{\top}\mathbf{w}^{\star})$. In the over-constrained case (i.e. the number of samples $n$ exceeds the input dimension $d$) with examples $(\mathbf{x}_i,\sigma(\mathbf{x}_i^{\top}\mathbf{w}^{\star}))$, it is sufficient to recover $\mathbf{w}^{\star}$ and hence achieve the Bayes risk. However, we prove that when the examples are labeled by hard labels $y_i$ sampled from the same conditional distribution $\sigma(\mathbf{x}_i^{\top}\mathbf{w}^{\star})$ and $\mathbf{w}^{\star}$ is $s$-sparse, then rotation-invariant algorithms are provably suboptimal: they incur an excess risk $\Omega\left(\frac{d-1}{n}\right)$, while there are simple non-rotation invariant algorithms with excess risk $O(\frac{s\log d}{n})$. The simplest rotation invariant algorithm is gradient descent on the logistic loss (with early stopping). A simple non-rotation-invariant algorithm for sparse targets that achieves the above upper bounds uses gradient descent on the weights $u_i,v_i$, where now the linear weight $w_i$ is reparameterized as $u_iv_i$. We conclude that rotation-invariant algorithms cannot efficiently learn noise-free sparse targets from hard labels.
Reinforcement Learning · Deep RL
Scaling network remains a bottleneck in deep reinforcement learning (RL): simply enlarging actor–critic networks destabilizes training and soon saturates performance. Although recent monolithic architectures such as SimBa and BRC have shown that carefully designed inductive biases can enable positive scaling up to a certain size, their improvements plateau soon as model parameters grow further. This work introduces ScaleMoE, a scalable RL architecture that integrates Mixture-of-Experts (MoE) modules into both the actor and critic of modern continuous control algorithms. Two complementary gating schemes are studied: output-level aggregation of per-expert policies and Q-functions, and feature-level fusion of expert representations before a shared head. We instantiate ScaleMoE on two representative monolithic RL baselines: the single-task method SimBa and the multi-task method BRC. Experiments across the DeepMind Control Suite, MetaWorld, and HumanoidBench show that progressively increasing the number of experts (up to 64) yields substantial improvements in returns, significantly outperforming monolithic networks of comparable or even greater parameter counts. Results demonstrate that ScaleMoE provides an efficient and effective scaling axis for deep RL in continuous control.
Applications · Computer Vision
Despite the generative capabilities of diffusion models, real-image editing remains constrained by a persistent trade-off between semantic editability and structural fidelity. We identify a primary cause of this limitation as the implicit coupling of editing progress with noise scale in existing paradigms. This coupling creates a budget misallocation: achieving stronger semantic changes often necessitates initializing from high-noise states, which can consume computation on disrupting global layout before semantic modification begins. To address this, we introduce NaviEdit, a training-free framework that decouples the editing trajectory from the denoising schedule via a strict Time-Axis Consistency principle. By reformulating editing as controlled vector field navigation on a distinct task axis, NaviEdit strategically concentrates the computational budget within semantically responsive intermediate scales while reducing exposure to destructive high-noise regimes. Experiments show that NaviEdit outperforms strong state-of-the-art baselines across PIE-Bench, achieving larger semantic edits with better structure preservation under comparable compute budgets, without requiring model tuning.
Deep Learning · Self-Supervised Learning
In this work, we address the critical yet underexplored challenge of symmetric multimodal-to-multimodal (MM2MM) retrieval, where queries and contexts are interchangeable. Existing universal multimodal retrieval works struggle with this task, as they are constrained by the labeled asymmetric datasets used. We produce SOLAR (Self-supervised jOint LeArning for symmetric multimodal Retrieval), a novel two-stage self-supervised framework that leverages readily available unlabeled web-scale image-text pairs. Based on the observation that both semantic alignment and discrepancies exist between two modalities, in the first stage, we learn the intersection mask of image-text pair, allowing us to align intersection while preserving semantic of difference. In the second stage, the learned mask is further utilized to construct positive and hardnegative samples via masking different parts of image/text, which enable us to conduct self-supervised multimodal embedding learning. Complementing this framework, we present a new benchmark featuring high-quality human-verified positive and hard-negative pairs to evaluate symmetric MM2MM retrieval under realistic conditions, as well as the corresponding pipeline. Extensive experiments against ten SOTA methods show SOLAR surpasses the strongest supervised VLM by 7.08 points on this benchmark, with over 50x fewer model parameters and a 5x smaller embedding dimension. Code will be available upon publication.
Applications · Social Sciences
Multi-agent debate (MAD) systems are often evaluated using binary correctness or peer agreement, yet such evaluations obscure how individual agents revise their answers during social interaction. We study the microscopic dynamics of answer revision in large language models (LLMs) using ConceptARC, a 2D grid-reasoning benchmark that admits quantitative distance measures between candidate solutions. By exposing a target model to controlled configurations of peer answers, we analyze how revision likelihood and direction depend on both social context and the distance between answers and the ground truth. We find that agents are more likely to revise when their answers are farther from the correct solution, and that revisions of incorrect answers exhibit a systematic contraction toward the ground truth, even when the final answer remains incorrect. Conversely, correct answers can be overturned by social pressure, particularly when wrong peers are near-correct. Together, these results show that multi-agent interaction induces structured, distance-aware movements in solution space that are invisible under binary correctness, clarifying when social reasoning leads to improvement, stability, or gradual regression in solution quality.
General Machine Learning · Clustering
Multi-view clustering aims to obtain a consensus clustering by integrating complementary and consistent information from multiple views. However, two critical challenges still exist in variational methods: (1) view heterogeneity and noise often make fusion unreliable; (2) ambiguous posteriors and misassigned boundary samples impact the clustering performance. To address these issues, we propose Dual-stage Contrastive Learning-enhanced Multi-view Variational Clustering (DCL-MVC), which integrates contrastive learning into both the fusion and representation stages. Firstly, at the fusion stage, we introduce a fusion-then-attention mechanism to capture cross-view interactions and learn view-level attention weights for building a unified and reliable fused representation, and further introduce instance-level contrastive learning to enforce cross-view alignment at the instance level. Secondly, we focus on boundary samples with uncertain posteriors and refine their cluster assignments by using cluster-center contrastive loss to enlarge inter-cluster margins, while leveraging prototypical contrastive learning with a confidence-aware curriculum to promote intra-cluster compactness at the representation stage. Extensive experiments on six real-world datasets demonstrate consistent improvements over strong baselines and validate the contribution of each component.
Deep Learning · Theory
We study post-training linear autoregressive models with outcome and process rewards. Given a context $\boldsymbol{x}$, the model must predict the response $\boldsymbol{y} \in \mathcal{Y}^N$, a sequence of length $N$ that satisfies a standard $\gamma$ margin assumption extended to sequences. We prove that on test samples where the base model achieves a non-trivial likelihood $\alpha$, a variant of policy gradient (PG) can achieve likelihood $1 - \varepsilon$ with an essentially minimax optimal number of reward queries $\tilde{\mathcal{O}}((\alpha^{-1} + \varepsilon^{-1})/\gamma^2)$. However, a barrier arises for going beyond the support of the base model. We prove that the overall expected error after post-training with outcome rewards is governed by a property of the base model we call the *Likelihood Quantile* (LQ), and that variants of PG, while minimax optimal, may require a number of reward queries exponential in $N$ to go beyond this support, regardless of the pre-training algorithm. To overcome this barrier, we study post-training with a process reward model, and demonstrate how PG variants in this setting avoid the curse of dimensionality in $N$ via dependence on a token-level LQ. Along the way, we prove that under the margin condition, SGD with adaptive learning rate (LR) achieves a near optimal test error for statistical learning, and PG with adaptive LR achieves a near optimal number of mistakes for online learning while being computationally efficient whenever possible, both of which may be of independent interest.
Deep Learning · Graph Neural Networks
Deep attribute graph clustering aims to learn discriminative node representations by leveraging both node attributes and graph topology to partition nodes into distinct clusters. Although substantial progress has been made in attribute-graph clustering in recent years, two key challenges remain: noisy edges in the original adjacency matrix degrade the quality of information propagation, and redundant feature information across different feature views hampers the learning of discriminative representations. To address these issues, we propose a self-supervised attribute graph clustering method based on topological reconstruction and correlation decorrelation. First, we reconstruct the graph topology by computing intersections between k-nearest neighbors and the original adjacency relationships, while simultaneously leveraging global semantic information from K-means clustering to filter out noisy nodes. This reconstructed topology effectively mitigates information redundancy during feature aggregation in Graph Neural Networks. Second, unlike existing augmentation-based contrastive methods, we treat the feature representations from an auto-encoder (AE) and a graph auto-encoder (GAE) as two complementary natural views. We then apply mutual information minimization and a decorrelation constraint to suppress redundant information between views, yielding more discriminative node representations. Extensive experiments on four widely-used graph datasets—ACM, DBLP, CITE, and AMAP—demonstrate that our method consistently outperforms six state-of-the-art baselines.
Theory · Optimization
Synchronization over the special Euclidean group $\mathrm{SE}(3)$ aims to recover absolute poses from noisy pairwise relative transformations and is a core primitive in robotics and 3D vision. Standard approaches often require multi-step heuristic procedures to recover valid poses, which are difficult to analyze and typically lack theoretical guarantees. This paper adopts a dual quaternion representation and formulates $\mathrm{SE}(3)$ synchronization directly over the unit dual quaternion. A two-stage algorithm is developed: A spectral initializer computed via the power method on a Hermitian dual quaternion measurement matrix, followed by a dual quaternion generalized power method (DQGPM) that enforces feasibility through per-iteration projection. The estimation error bounds are established for spectral estimators, and DQGPM is shown to admits a finite-iteration error bound and achieves linear error contraction up to an explicit noise-dependent threshold. Experiments on synthetic benchmarks and real-world multi-scan point-set registration demonstrate that the proposed pipeline improves both accuracy and efficiency over representative matrix-based methods.
Reinforcement Learning · Multi-agent
Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on inefficient information exchange or fail to transmit sufficient state information. To address this, we propose LLM-driven Multi-Agent Communication (LMAC), which leverages an LLM's reasoning capability to design a communication protocol that enables all agents to reconstruct the underlying state as accurately and uniformly as possible. LMAC iteratively refines the protocol using an explicit state-awareness criterion, improving state recovery while narrowing differences in agents' knowledge. Experiments on diverse MARL benchmarks show that LMAC improves state reconstruction across agents and yields substantial performance gains over prior communication baselines.