Contrastive learning has emerged as a powerful paradigm for self-supervised representation learning, yet the precise conditions under which it recovers meaningful latent structure remain incompletely understood. We develop a measure-theoretic framework that formalizes the diversity condition, a requirement on the sampling mechanism that is necessary for recovering the latent space up to orthogonal transformation. We prove that when this condition is violated, as commonly occurs in practical settings where augmentations preserve semantic content, the optimal encoder no longer preserves geometric structure and linear identifiability is lost. Crucially, we demonstrate that the contrastive loss alone is insufficient for latent space reconstruction: encoder inductive bias emerges as a critical component that compensates for violations of the diversity condition. Our experiments on synthetic datasets and CIFAR-10 confirm these theoretical predictions, showing that architectural constraints become essential precisely when sampling diversity is limited. These findings have direct implications for the design of data augmentation strategies and encoder architectures in self-supervised contrastive learning systems.
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 · Language, Speech and Dialog
Real-time and accurate spatial audio generation is pivotal for delivering an immersive experience. However, existing spatial audio synthesis technologies are often encumbered by a tradeoff between generation quality and high inference latency, as well as difficulty in capturing precise spatial information from multimodal inputs. To address these challenges, we propose S3Audio, a unified streaming framework for high-fidelity spatial audio generation from panoramic videos and text prompts. S3Audio mainly makes the following contributions: 1) We introduce a causal autoregressive diffusion transformer architecture that enables streaming high-quality spatial audio generation. 2) We design a Spatial Video–Audio Contrastive (SVAC) learning strategy to align the video encoder with the acoustic domain, and further employ a multi-objective online direct preference optimization~(ODPO) scheme, resulting in strong spatial perception and robust multimodal spatial audio synthesis. 3) To alleviate the current scarcity of spatial audio datasets, we also develop an automated annotation pipeline for generating detailed spatial captions. Experimental results demonstrate that S3Audio achieves superior performance in both video-to-spatial and text-to-spatial audio generation tasks. Demos can be found at: \url{https://s3audio.github.io}
Applications · Computer Vision
Multimodal large language models (MLLMs) have recently made strong progress in vision-language reasoning, yet their performance often degrades as generations grow longer. A key factor is that they frequently lose track of earlier visual evidence and intermediate constraints under a monolithic growing context. Inspired by how humans separately recall what they see and what they infer when solving complex tasks, we propose DLMR, a parameter-efficient mechanism that equips MLLMs with dual latent memories: a visual memory that compresses image evidence and a reasoning memory that tracks intermediate conclusions and constraints. A router then dynamically decides which memory and how much to reuse during inference, preserving visual grounding while maintaining coherent long-horizon reasoning. DLMR is trained in three stages from latent memory construction to selective router learning while keeping the base MLLM frozen, yielding substantial gains on both general and reasoning benchmarks with only a small number of additional trainable parameters. Further analyses reveal interpretable, state-dependent routing in which the visual and reasoning memories specialize as intended, and demonstrate that this design reduces redundant decoding and improves token efficiency over long generations.
Deep Learning · Large Language Models
Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4 or HQQ) offer maximum accessibility but suffer from functional collapse at extreme bit-rates below 4 bits. On the other hand, techniques leveraging calibration data or extensive recovery training achieve superior fidelity but impose high computational constraints and face uncertain robustness under data distribution shifts. We introduce EntQuant, the first framework to unite the advantages of these distinct paradigms. By matching the performance of data-dependent methods with the speed and universality of data-free techniques, EntQuant enables practical utility in the extreme compression regime. Our method decouples numerical precision from storage cost via entropy coding, compressing a 70B parameter model in less than 30 minutes. We demonstrate that EntQuant does not only achieve state-of-the-art results on standard evaluation sets and models, but also retains functional performance on more complex benchmarks with instruction-tuned models, all at modest inference overhead.
Theory · Online Learning and Bandits
In this paper, we study dynamic regret in unconstrained online convex optimization (OCO) with movement costs. Specifically, we generalize the standard setting by allowing the movement cost coefficients $\lambda_t$ to vary arbitrarily over time. Our main contribution is a novel algorithm that establishes the first comparator-adaptive dynamic regret bound for this setting, guaranteeing $\widetilde{\mathcal{O}}(\sqrt{(1+P_T)(T+\sum_t \lambda_t)})$ regret, where $P_T$ is the path length of the comparator sequence over $T$ rounds. This recovers the optimal guarantees for both static and dynamic regret in standard OCO as a special case where $\lambda_t=0$ for all rounds. To demonstrate the versatility of our results, we consider two applications: *OCO with delayed feedback* and *OCO with time-varying memory*. We show that both problems can be translated into time-varying movement costs, establishing a *novel reduction* specifically for the delayed feedback setting that is of independent interest. A crucial observation is that the first-order dependence on movement costs in our regret bound plays a key role in enabling optimal comparator-adaptive dynamic regret guarantees in both settings.
Applications · Time Series
Causal discovery in time series is increasingly performed using nonlinear machine-learning models, yet the resulting causal relationships are almost always summarized by scalar edge scores. We argue that this practice obscures the true object learned by nonlinear autoregressive models: function-valued causal influence. In such models, each directed relationship corresponds not to a single weight or coefficient, but to a state-dependent function whose effect varies across regimes, magnitudes, and contexts of the system. In this paper, we formalize function-valued causal influence in nonlinear multivariate time series and show that common scalar summaries, such as aggregated contribution magnitudes, constitute severe information bottlenecks. Using Neural Additive Vector Autoregression as a representative architecture, we demonstrate that edges with indistinguishable scalar causal scores can exhibit qualitatively different functional behaviors, including monotonic, thresholded, saturating, and sign-changing effects. These differences explain persistent discrepancies between causal score magnitude, interpretability, and predictive relevance that cannot be resolved by significance testing alone. We present a general framework for extracting and visualizing causal response functions from neural autoregressive models using learned contribution tensors and local attribution methods. Through controlled synthetic systems and an applied case study of democratic development, we show how function-valued analysis reveals regime-specific and asymmetric causal structure that is systematically missed by coefficient-centric or score-centric approaches. Our results suggest that meaningful interpretation of nonlinear causal time-series models requires moving beyond scalar causal scores toward explicit analysis of causal response functions. This reframing clarifies the representational content of modern causal discovery methods and provides a foundation for more faithful interpretation of complex dynamical systems.
Deep Learning · Theory
Transformers pretrained via next token prediction learn to factor their world into parts, representing these factors in orthogonal subspaces of the residual stream. We formalize two representational hypotheses: (1) a representation in the product space of all factors, whose dimension grows exponentially with the number of parts, or (2) a factored representation in orthogonal subspaces, whose dimension grows linearly. Both track context-induced uncertainty over the latent parts, but the factored representation sacrifices fidelity when factors are not conditionally independent. We derive precise predictions about the geometric structure of activations for each, including the number of subspaces, their dimensionality, and the arrangement of context embeddings within them. We test between these hypotheses on transformers trained on synthetic processes with known latent structure. When factors are conditionally independent, models learn factored representations; when noise or dependencies break this structure, models gradually expand their effective dimensionality over training to recover fidelity. This provides a principled explanation for why transformers decompose the world into parts, and suggests that interpretable low dimensional structure may persist even in models trained on complex data.
Applications · Chemistry, Physics, and Earth Sciences
With the continuous advancement of reasoning abilities in Large Language Models (LLMs), their application to scientific reasoning tasks has gained significant research attention. Current research primarily emphasizes boosting LLMs' performances on scientific QA benchmarks by training on larger, more comprehensive datasets with extended reasoning chains. However, these approaches neglect the essence of scientific reasoning process -- logicality, which is the rational foundation to ensure the validity of reasoning steps leading to reliable conclusions. In this work, we make the first systematic investigation into the internal logicality underlying LLM scientific reasoning, and develop a scientific logicality enriched methodology, including a set of assessment criteria and data sampling methods for logicality-guided training, to improve the logical faithfulness as well as task performance. Further, we take physics, characterized by its diverse logical structures and formalisms, as an exemplar discipline to practise the above methodology. For data construction, we extract scientific problems from academic literature and sample a high-quality dataset exhibiting strong logicality. Experiments based on three different backbone LLMs reveal that: 1) the training data we constructed can effectively improve the scientific logicality in LLM reasoning; and 2) the enriched scientific logicality plays a critical role in solving scientific problems.
Reinforcement Learning · Deep RL
Many modern retrieval problems are \emph{set-valued}: given a broad intent, the system must return a \emph{collection} of results that optimizes higher-order properties (e.g., diversity, coverage, complementarity, coherence) while staying grounded to a fixed database. Set-valued objectives are inherently non-decomposable and are not captured by existing supervised (query, content) datasets which only prioritize top-1 retrieval. While reinforcement learning (RL) can optimize set-level objectives via interaction, deploying an RL-tuned LLM for fan-out retrieval is prohibitively expensive at query time. Conversely, diffusion-based generative retrieval enables efficient single-pass fan-out in embedding space, but requires objective-aligned training targets. To address these issues, we propose {R4T (Retrieve-for-Train)}, which uses RL \emph{once} as an objective transducer in a three step process: (i) train a fan-out LLM with composite set-level rewards, (ii) synthesize objective-consistent training pairs, and (iii) train a lightweight diffusion retriever to model the conditional distribution of set-valued outputs. Across Polyvore and a music playlist dataset, R4T improves retrieval quality over strong baselines while reducing query-time fan-out latency by an order of magnitude.
Theory · Reinforcement Learning and Planning
Kullback-Leibler divergence (KL) regularization is widely used in reinforcement learning, but it becomes infinite under support mismatch and can degenerate in low-noise limits. Utilizing a unified information-geometric framework we introduce (Kalman)-Wasserstein-based KL analogues by replacing the Fisher–Rao geometry in the dynamical formulation of the KL with transport-based geometries, and we derive closed-form values for common distribution families. These divergences remain finite under support mismatch and yield a geometric interpretation of regularization heuristics used in Kalman ensemble methods. We demonstrate the utility of these divergences in KL-regularized optimal control. In the fully tractable setting of linear time-invariant systems with Gaussian process noise, the classical KL reduces to a quadratic control penalty that becomes singular as process noise vanishes. Our variants remove this singularity and yield well-posed problems. On a double integrator and a cart-pole example, the resulting controls outperform KL-based regularization.
Theory · Game Theory
We study the problem of fairly allocating indivisible goods to agents in an online setting, where goods arrive sequentially and must be allocated irrevocably. Focusing on the popular fairness notions of envy-freeness, proportionality, and maximin share fairness (and their approximate variants), we investigate how access to future information changes what guarantees are achievable. Without any information, we prove strong impossibility results even for approximate fairness. With normalization information (agents' total values), we provide an algorithm that achieves stronger fairness guarantees than previously known results, and show matching impossibilities for stronger notions. With frequency predictions (value multisets without order), we design a meta-algorithm that lifts a broad class of offline "share-based" guarantees to the online setting, matching the best-known offline bounds. Finally, we provide learning-augmented variants of both models: under noisy totals or noisy frequency predictions, our guarantees are robust and degrade gracefully with the error parameters.
Optimization · Everything Else
A fundamental challenge in data science is to match disparate point sets with each other. While optimal transport efficiently minimizes point *displacements* under a bijectivity constraint, it is inherently sensitive to rotations. Conversely, minimizing *distortions* via the Gromov-Wasserstein (GW) framework addresses this limitation but introduces a non-convex, computationally demanding optimization problem. In this work, we identify a broad class of distortion penalties that reduce to a simple alignment problem within a lifted feature space. Leveraging this insight, we introduce an iterative GW solver with a linear memory footprint and quadratic (rather than cubic) time complexity. Our method is differentiable, comes with strong theoretical guarantees, and scales to hundreds of thousands of points in minutes. This efficiency unlocks a wide range of geometric applications and enables the exploration of the GW energy landscape, whose local minima encode the symmetries of the matching problem.
Applications · Health / Medicine
Oncologists are increasingly relying on multiple modalities to model the complexity of diseases. Within this landscape, transcriptomic and epigenetic data have proven to be particularly instrumental and play an increasingly vital role in clinical applications. However, their integration into multimodal models remains a challenge, especially considering their high dimensionality. In this work, we present a novel bimodal model that jointly learns representations of bulk RNA-seq and DNA methylation leveraging self-supervision from masked language modeling. We leverage an architecture that reduces the memory footprint usually attributed to purely transformer-based models when dealing with long sequences. We demonstrate that the obtained bimodal embeddings can be used to fine-tune cancer-type classification and survival models that achieve state-of-the-art performance compared to unimodal models. Furthermore, we introduce a robust learning framework that maintains downstream task performance despite missing modalities, enhancing the model’s applicability in real-world clinical settings.
Reward shaping can accelerate reinforcement learning, but in sparse-reward \emph{offline} multi-agent RL it is often brittle: dense intrinsic rewards may alter the underlying Markov game, while world-model guidance can amplify model bias. We find that shaping becomes reliable when it is (i) activated only after \emph{statistically validated} learning plateaus and (ii) constrained to \emph{potential-based} shaping, which preserves the task optimum. Motivated by this, we propose \textsc{SOLAR}, a simulate--evaluate--shape framework. A learned world model enables low-cost rollouts to test plateaus; once a plateau is detected, we inject shaping in the form $r+\gamma\Phi(s')-\Phi(s)$ with adaptively updated potentials; and we attenuate shaping using uncertainty-aware throttling in unreliable regions. We provide theoretical analysis on policy invariance and on the deviation of plateau decisions under model error, and establish stability for the resulting two-timescale adaptation. Experiments on sparse-reward offline MARL benchmarks show consistent gains in stability and final performance across dataset qualities.
Applications · Chemistry, Physics, and Earth Sciences
Density functional theory (DFT) is the most widely used method for calculating molecular properties; however, its accuracy is often insufficient for quantitative predictions. Coupled cluster (CC) theory is the most successful method for achieving accuracy beyond DFT and predicting properties that closely align with experiment. It is known as the ``gold standard'' of quantum chemistry. Unfortunately, the high computational cost of CC limits its widespread applicability. In this work, we present the Molecular Orbital Learning Model (MoLe), an equivariant machine learning model that directly predicts CC's core mathematical objects, the excitation amplitudes, from the mean-field Hartree-Fock molecular orbitals as inputs. We test various aspects of our model and demonstrate its very high data efficiency and remarkable out-of-distribution generalization to larger molecules and off-equilibrium geometries, despite being trained only on small equilibrium geometries. Finally, we also examine its ability to reduce the number of cycles required to converge CC calculations. MoLe can set the foundations for high-accuracy wavefunction-based ML architectures to accelerate molecular design and complement force-field approaches.
Workflow optimization for tool-using LLM agents is often cast as global search over candidate graphs, scored by a scalar metric. This collapses rich, multi-step failure traces into binary outcomes, obscuring recurring failure structure and making refinement inefficient. We reframe optimization as \emph{distributional refinement}: each workflow induces a density over a \textbf{Failure Signature Space} $\mathcal{F}$, and the goal is to minimize its \textbf{Expected Failure Mass}. We propose \textbf{CE-Graph}, which maintains a counterexample pool, estimates dense failure modes, and applies operator-constrained graph edits via a \textbf{Propose-and-Verify} loop with a convergence-aware stopping rule. Across math, code, and QA benchmarks, CE-Graph improves robustness while reducing optimization cost compared to strong workflow-search baselines, suggesting reliability emerges from learning and reshaping failure landscapes rather than merely maximizing aggregate success rates.
General Machine Learning · Everything Else
Testing conditional independence is a fundamental yet inherently difficult challenge, as controlling Type I error is impossible in general. The recently popular "Model-X" paradigm offers a solution by relying on a perfectly known conditional distribution. In traditional "one-shot" testing regimes, slight deviations from perfect knowledge are sometimes allowable, but existing work in more realistic online settings has required exact adherence to Model-X. We propose a new approach for sequential testing of conditional independence that is far more robust to estimation errors in the conditional distribution. Our method, based on online optimization of the Kernel Conditional Independence statistic, introduces a novel normalization and "truncate-and-shift" calibration strategy to the testing-by-betting paradigm. This framework greatly improves validity with estimated conditionals while still providing high power across high-dimensional synthetic benchmarks and real-world fairness tasks.
Long-tailed multi-label text classification is often treated as a data scarcity problem, addressed by re-sampling or fixed re-weighting. We argue that a central failure mode is \textit{dominant coalition capture}: frequent labels, amplified by spurious co-occurrences, form dominant coalitions that dominate shared representations and gradient allocation during optimization. As a result, rare labels are learned via superficial shortcuts, yielding brittle generalization under distribution shifts. We propose \textbf{NBCG}, a Nash-Bargained Causal Game that reformulates multi-label learning as a cooperative bargaining process among label coalitions. NBCG first leverages Neural Structural Equation Models to learn a directed dependency structure, inducing causally coherent coalitions---rather than random partitions---and coalition-specific communication masks. We then optimize a Nash bargaining objective over coalition utilities relative to an adaptive disagreement point, which serves as a principled credit-allocation mechanism: it adaptively prioritizes under-served coalitions while maintaining a Pareto-efficient trade-off among all players.
Reinforcement Learning · Planning
In this paper, we propose a general theory of ambiguity-averse MDPs, which treats the uncertain transition probabilities as random variables and evaluates a policy via a risk measure applied to its random return. This ambiguity-averse MDP framework unifies several models of MDPs with epistemic uncertainty for specific choices of risk measures. We extend the concepts of value functions and Bellman operators to our setting. Based on these objects, we establish the consequences of dynamic programming principles in this framework (existence of stationary policies, value and policy iteration algorithms), and we completely characterize law-invariant risk measures compatible with dynamic programming. Our work draws connections among several variants of MDP models and fully delineates what is possible under the dynamic programming paradigm and which risk measures require leaving it.
Deep Learning · Algorithms
Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from a scalar outcome reward per attempt, creating a severe credit-assignment bottleneck. Many verifiable environments actually provide rich textual feedback, such as runtime errors or judge evaluations, that explain *why* an attempt failed. We formalize this setting as reinforcement learning with rich feedback and introduce **Self-Distillation Policy Optimization** (**SDPO**), which converts tokenized feedback into a dense learning signal without any external teacher or explicit reward model. SDPO treats the current model conditioned on feedback as a self-teacher and distills its feedback-informed next-token predictions back into the policy. In this way, SDPO leverages the model's ability to retrospectively identify its own mistakes in-context. Across scientific reasoning, tool use, and competitive programming on LiveCodeBench v6, SDPO improves sample efficiency and final accuracy over strong RLVR baselines. Notably, SDPO also outperforms baselines in standard RLVR environments that only return scalar feedback by using successful rollouts as implicit feedback for failed attempts. Finally, applying SDPO to individual questions at test time accelerates discovery on difficult binary-reward tasks, achieving the same discovery probability as best-of-k sampling or multi-turn conversations with 3x fewer attempts.