论文检索

Applications · Neuroscience, Cognitive Science

Mathis Pink, Vy Vo, Qinyuan Wu, Jianing Mu, Javier Turek, Uri Hasson, Kenneth Norman, Sebastian Michelmann, Alexander Huth, Mariya Toneva

Human episodic memory supports the retrieval of experiences that unfold over extended timescales, yet the computational mechanisms underlying this ability remain debated due to the difficulty of mechanistic accessibility in long-term memory experiments in humans. Long-context LLMs may offer promising ways to reveal plausible computational mechanisms that drive this type of retrieval. Here, we investigate whether and, if so, how LLMs capture core behavioral signatures of humans of a central aspect of episodic memory via a temporal order memory task. Using a new dataset of human behavior based on a full-length novel, we show substantial similarities between the human and model performances on the temporal order memory task. We next perform long-context mechanistic interpretability analyses to reveal the underlying mechanisms in the model, and find that model performance relies on a one-dimensional temporal code that is reinstated during retrieval by a single time-reinstatement attention head. These findings support temporal context reinstatement as an important mechanism for episodic-like temporal-order memory in LLMs, offering new insights into how temporal aspects of long-term episodic memory may be instantiated in both artificial and biological systems.

Deep Learning · Theory

Austin Feng, Marius Alonso, Ambroise Odonnat, Vasilii Feofanov, Ievgen Redko

Self-consistency (SC) is a widely-used test-time inference technique for improving performance in chain-of-thought reasoning. It consists of generating multiple responses, or ``samples," from a large language model (LLM) and selecting the most frequent answer. This procedure can naturally be viewed as a majority vote or empirical mode estimation. Despite its effectiveness, self-consistency is prohibitively expensive at scale when naively applied to datasets, and it lacks a unified theoretical treatment of sample efficiency and scaling behavior. In this paper, we provide the first comprehensive analysis of SC's scaling behavior and its variants, drawing on mode estimation and voting theory. We derive and empirically validate power law scaling for self-consistency across datasets, and analyze the sample efficiency for fixed-allocation and dynamic-allocation sampling schemes. From these insights, we introduce Blend-ASC, a novel variant of self-consistency that dynamically allocates samples to questions during inference, achieving state-of-the-art sample efficiency. Our approach uses $4.8\times$ fewer samples than vanilla SC on average, outperforming both fixed- and dynamic-allocation SC baselines, thereby demonstrating the superiority of our approach in terms of efficiency. In contrast to existing variants, we note that Blend-ASC is hyperparameter-free and can fit any budget of samples, ensuring it can be easily applied to any self-consistency application.

Optimization · Discrete and Combinatorial Optimization

Dian Meng, Zhiguang Cao, Yaoxin Wu, Yaqing Hou

Multi-task vehicle routing solvers via deep reinforcement learning have attracted broad attention and achieved significant progress in handling multiple constraints. However, existing neural solvers still face critical challenges, including insufficient representation, unstable training, and inefficient exploration in large combinatorial action spaces, which often prevents performance from meeting its full potential. To address these issues, we propose PoMtVRS (Preference-Optimized Multi-Task Vehicle Routing Solver with Preference Gating), a plug-and-play framework that jointly improves decoder representations and exploration efficiency through a synergistic combination of decoder-side augmentation and preference-driven optimization. Specifically, we introduce the preference optimization objective to learn relative comparisons among candidate solutions for different routing tasks, encouraging a higher generation probability of better solutions. Meanwhile, we design a preference-gated block that adaptively modulates decoder representations via sparse gated attention and nonlinear residual refinement. Extensive experiments demonstrate that PoMtVRS elevates state-of-the-art unified neural VRP backbones, achieving leading performance in multi-task benchmarks and stronger generalization.

Shishang Wu, Bingjing Tang, Vinayak A Rao

Generative models such as diffusion models and transformers are powerful tools for learning complex data distributions and generating new samples. However, their black-box nature limits interpretability, and the learned distributions may violate side knowledge arising from domain expertise. We represent such side knowledge as probability distributions over noisy functions of the modeled objects and seek to minimally adjust the generative model to satisfy such constraints. Our approach is to optimize the dual of the corresponding constrained optimization problem, encoding the infinite-dimensional dual variable using a neural network. We introduce a simple and efficient score-based method for fitting the parameters of this neural network, and for simulating from the resulting adjusted distribution. We evaluate our approach on a number of synthetic tasks, as well on two real-world problems: a regularized nonparametric maximum likelihood estimation problem, and the incorporation of class-level fairness constraints into image diffusion models.

Social Aspects · Accountability, Transparency, and Interpretability

Adi Simhi, Fazl Barez, Martin Tutek, Yonatan Belinkov, Shay Cohen

How does the conversational past of large language models (LLMs) influence their future performance? Recent work suggests that LLMs are affected by their conversational history in unexpected ways. For instance, hallucinations in prior interactions may influence subsequent model responses. In this work, we introduce History Echoes, a framework that investigates how conversational history biases subsequent generations. The framework explores this bias from two perspectives: probabilistically, we model conversations as Markov chains to quantify state consistency; geometrically, we measure the consistency of consecutive hidden representations. Across three model families and six datasets spanning diverse phenomena, our analysis reveals a strong correlation between the two perspectives. By bridging these perspectives, we demonstrate that behavioral persistence manifests as a geometric trap, where gaps in the latent space confine the model's trajectory.

Deep Learning · Theory

Zheng-An Chen, Pengxiao Lin, Zhi-Qin John Xu, Tao Luo

Transformer-based models have achieved remarkable success across a wide range of domains, yet our understanding of their training dynamics remains limited. In this work, we identify a recurrent focus–dilution cycle in attention learning and provide a rigorous explanation in a one-layer Transformer setting for Markovian data via gradient-flow analysis. Using stage-wise linearization around critical points, we show that a single focus–dilution cycle can be decomposed into a sequence of distinct stages. First, embedding and projection rapidly condense to a rank-one structure, while attention parameters remain effectively frozen. Then, the attention parameters begin to increase, inducing a frequency-driven focus toward high-frequency tokens. As attention continues to evolve, it generates next-order perturbations in embeddings, leading to a mass-redistribution mechanism that progressively dilutes this focus. Finally, small asymmetries among low-frequency tokens lift a degenerate critical point, opening new embedding directions and initiating the next cycle. Experiments on synthetic Markovian data as well as WikiText and TinyStories corroborate the predicted stages and cyclical dynamics.

Social Aspects · Accountability, Transparency, and Interpretability

Satoru Utsunomiya, Masaru Isonuma, Junichiro Mori, Ichiro Sakata

As generative AI faces intensifying legal challenges, the machine learning community has increasingly relied on *post-hoc mitigation*---especially machine unlearning and inference-time guardrails---to argue for compliance. **This paper argues that such post-hoc mitigation methods cannot retroactively cure liability from unlawful acquisition and training, because compliance hinges on data lineage, not the outputs.** Our argument has three parts. First, unauthorized copying/ingestion can be a legally complete *completed act*, and model weights may operate as *fixed copies* that retain training-derived expressive value, making later filtering beside the point for infringement. Second, *contract* and *tort/unfair-competition* rules---via licenses, terms of service, and anti-free-riding principles---can independently restrict access and use, often bypassing copyright defenses (e.g., fair use or TDM exceptions). Third, since value from protected inputs can persist in weights, remedies such as *unjust enrichment* and *disgorgement* may require stripping gains and, in some cases, reaching the model itself. We therefore argue for a shift from *Post-Hoc Sanitization* to verifiable *Ex-Ante Process Compliance*.

Applications · Neuroscience, Cognitive Science

Fenghao Liu, Yipeng Shen, Peng Chen, Qian Zheng, Peng Lin, Gang Pan

Processing long sequence data such as speech requires models to maintain long-term dependencies, which is challenging for recurrent spiking neural networks due to high temporal dynamics in neuron models that leak stored information in their membrane potentials, and due to vanishing gradients during backpropagation through time. These issues can be mitigated by employing more complex neuron designs, such as ALIF and TC-LIF, but these neuron-level solutions often incur high computational costs and complicate hardware implementation, undermining the efficiency advantages of Spiking neural networks. Here we propose an architectural-level solution that leverages the dynamical interactions of a few leaky integrate-and-fire (LIF) neurons to enhance long-term information storage. The memory capability of this LIF-based micro-circuit is adaptively modulated by global recurrent connections of the recurrent spiking neural network, contributing to selective enhancement of temporal information retention, and promoting stable gradient propagation through time. The proposed model outperforms previous methods including LSTM, ALIF, and TC-LIF in long sequence tasks, achieving 96.52\% accuracy on the PS-MNIST dataset. Furthermore, our method also provides a compelling efficiency advantage, yielding up to 277$\times$ computational efficiency improvement compared to conventional models such as LSTM. This work paves the way for building cost-effective, hardware-friendly, and interpretable spiking neural networks for long sequence modeling.

Applications · Health / Medicine

Salma Ahmed, Emad Mohammed, Azam Bidgoli

Modern segmentation models achieve strong predictive performance but remain largely opaque, limiting our ability to diagnose failures, understand dataset shift, or intervene in a principled manner. We introduce $\textbf{Med-SegLens}$, a model-diffing framework that decomposes segmentation model activations into interpretable latent features using sparse autoencoders trained on SegFormer and U-Net. Through cross-architecture and cross-dataset latent alignment across healthy, adult, pediatric, and sub-Saharan African glioma cohorts, we identify a stable backbone of shared representations, while dataset shift is driven by differential reliance on population-specific latents. We show that these latents act as causal bottlenecks for segmentation failures, and that targeted latent-level interventions can correct errors and improve cross-dataset adaption without retraining, recovering performance in 70% of failure cases and improving Dice score from 39.4% to 74.2%. Our results demonstrate that latent-level model diffing provides a practical and mechanistic tool for diagnosing failures and mitigating dataset shift in segmentation models.

Applications · Health / Medicine

Moritz Schaefer, Zoe Piran, Nils Philipp Walter, Animesh Awasthi, Christoph Bock, Jure Leskovec, Zinaida Good

AI-driven disease characterization in histopathology promises to assist in clinical decision making, but its performance is limited by the scarcity of detailed annotations. In contrast, single-cell gene expression provides expressive and interpretable labels that compensate this scarcity, but assays are costly and rarely acquired in clinical workflows. To overcome this gap, we propose to bridge these data sources using a trimodal contrastive learning framework that aligns histopathology images, gene expression profiles, and natural-language descriptions. Our training data combines atlas-scale datasets of (i) spatially-resolved gene expression paired with histopathology images, and (ii) single-cell gene expression with curated annotations. Together, these data induce an alignment between image and text modalities, which we leverage for zero-shot image annotation tasks, such as the identification of immune cells. We present a sufficient condition under which this transfer can succeed and assess the performance of our approach against established baselines. We predict cell types at 15.4\% improved relative AUROC over leading pathology vision language models. Our method also exhibits significant gains across diverse prediction tasks in low-data regimes, when combining training data from all three modality pairs. Our work thus establishes *transitive representation learning* as an effective strategy to enhance histopathology interpretation.

Optimization · Discrete and Combinatorial Optimization

Oguzhan Gungordu, Siheng Xiong, Faramarz Fekri

Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks' reliance on fixed evolutionary rules and static prompt templates often leads to myopic heuristic generation, redundant evaluations, and limited reasoning about how new heuristics should be derived. We propose a novel multi-agent reasoning framework, referred to as Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs (PathWise), which formulates heuristic generation as a sequential decision process over an entailment graph serving as a compact, stateful memory of the search trajectory. This approach allows the system to carry forward past decisions and reuse or avoid derivation information across generations. A policy agent plans evolutionary actions, a world model agent generates heuristic rollouts conditioned on those actions, and critic agents provide routed reflections summarizing lessons from prior steps, shifting LLM-based AHD from trial-and-error evolution toward state-aware planning through reasoning. Experiments across diverse COPs show that PathWise converges faster to better heuristics, generalizes across different LLM backbones, and scales to larger problem sizes.

Deep Learning · Large Language Models

YaoQi Fan, Zhe Chen, Wei Zhu, Kangxin Yin, Yangzhou Liu, Yue Cao, Zhi Zhu, Tong Lu

Vision–Language Models (VLMs) are increasingly deployed with web search tools, yet we still lack benchmarks that isolate a critical capability for real-world use: deciding when to search and how to steer search from ambiguous visual evidence, especially when multiple images provide overlapping or conflicting cues. We introduce NAVIGATE, a novel benchmark centered on images as primary evidence for open-web search planning and multi-step reasoning. It contains 500 questions across 20 domains and spans three difficulty tiers, from single-image, self-contained problems to multi-image joint search and multi-domain composition. Unlike prior benchmarks that specify explicit search targets, NAVIGATE evaluates search decision-making: models must infer whether external search is necessary and iteratively refine search directions based on holistic reasoning over visual cues. Across a broad set of VLMs and search-enabled systems, performance remains low, Gemini-3-Pro-Preview-Search reaches only 36.4% accuracy, highlighting persistent failures in cross-image grounding, search triggering, and search strategy coordination. We will release NAVIGATE publicly.

General Machine Learning · Representation Learning

Sangli Teng, Hang Liu, Koushil Sreenath

This work proves that an $n$-dimensional hybrid system can be embedded into an $m$-dimensional Euclidean space equipped with a continuous vector field on its embedded image whenever $m>2n$. This result suggests that an *intrinsically* discontinuous hybrid system generically admits a continuous *extrinsic* representation that is well-posed for differentiable optimization. Building on this existence theorem, we show that a latent Neural ODE with consistency loss in both the latent and state space can accurately recover the flow of hybrid systems. Extensive experiments suggest the proposed method outperforms the existing method in learning hybrid systems with varying geometries from only time series data.

Reinforcement Learning · Online

Haruka Kiyohara, Mihaela Curmei, Ariel Evnine, Shankar Kalyanaraman, Israel Nir, Ana-Roxana Pop, Nitzan Razin, Sarah Dean, Thorsten Joachims, Udi Weinsberg

Large-scale search, recommendation, and retrieval-augmented generation (RAG) systems typically employ a two-stage architecture: an early-stage ranker (ESR) generates a candidate set, which is subsequently re-ranked by a late-stage ranker (LSR). While there are many reinforcement learning (RL) methods for training the LSR, end-to-end training of the ESR has proven challenging. In particular, naive application of "vanilla" policy gradient (V-PG) is not scalable for candidate-set sizes relevant for practical use due to exploding variance. This issue arises because V-PG propagates the gradient to the joint probability of the candidate sets, ignoring the contribution of each specific item in the candidate set to the reward. To mitigate this issue, we propose a novel *"credit-assigned" PG (CA-PG)*, which computes gradients with respect to the probability that the target item is chosen in any candidate set, i.e. marginalizing over all candidate sets that contain it. Our theoretical analysis reveals that CA-PG significantly reduces the variance of V-PG by marginalizing over the specific composition of the candidate set, while preserving the ability to learn the correct ranking of actions under a reasonably aligned LSR policy. Experiments on both synthetic and real-world data demonstrate that CA-PG improves the convergence speed and training stability for ESRs utilizing the canonical Plackett-Luce model, especially when the candidate-set size is large.

Optimization · Discrete and Combinatorial Optimization

Florian Adriaens, Nikolaj Tatti

Correlation clustering is a classic approach for summarizing signed graphs, where the goal is to cluster the graph while minimizing positive inter-cluster edges plus negative intra-cluster edges. On complete signed graphs, correlation clustering is closely related to the bad triangle traversal (BTT) problem of finding the smallest number of edges that need to be removed such that the remaining graph does not have a bad triangle. Here, a bad triangle is a triangle with exactly one negative edge. A known result states that a feasible bad triangle cover $F$ on a complete signed graph can be transformed into a correlation clustering with at most $2|F|$ mistakes. In this paper we improve this ratio to $\frac{3}{2}|F|$ mistakes using a pivot-based method. We also propose novel 2-approximations for BTT. Using a recent result on approximating the bad triangle cover LP, we obtain an $(2+\epsilon)$ approximation in time almost equal to the time needed to find a maximal set of edge-disjoint bad triangles (which would give a standard 3-approximation). Additionally, several inapproximability results are provided. For general signed graphs, a better than 2-approximation is unlikely as our problem can be used to approximate vertex cover. For complete signed graphs, it is NP-hard to approximate with factor better than $\frac{2137}{2136}$. This result also holds for several other related problems.

Applications · Language, Speech and Dialog

Haoran Luo, Haihong E, Guanting Chen, Qika Lin, Yikai Guo, Fangzhi Xu, Zemin Kuang, Meina Song, Xiaobao Wu, Yifan Zhu 等

Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as entity-relation graphs, but still face challenges in high construction cost, fixed one-time retrieval, and reliance on long-context reasoning and prompt design. To address these challenges, we propose Graph-R1, an agentic GraphRAG framework via end-to-end reinforcement learning (RL). It introduces lightweight knowledge hypergraph construction, models retrieval as a multi-turn agent-environment interaction, and optimizes the agent process via an end-to-end reward mechanism. Experiments on standard RAG datasets show that Graph-R1 outperforms traditional GraphRAG and RL-enhanced RAG methods in reasoning accuracy, retrieval efficiency, and generation quality. Our code is available.

Optimization · Stochastic

Dimitris Oikonomou, Nicolas Loizou

The stochastic Polyak step size (SPS) has proven to be a promising choice for stochastic gradient descent (SGD), delivering competitive performance relative to state-of-the-art methods on smooth convex and non-convex optimization problems, including deep neural network training. However, extensions of this approach to non-smooth settings remain in their early stages, often relying on interpolation assumptions or requiring knowledge of the optimal solution. In this work, we propose a novel SPS variant, Safeguarded SPS (SPS$_{safe}$), for the stochastic subgradient method, and provide rigorous convergence guarantees for non-smooth convex optimization with no need for strong assumptions. We further incorporate momentum into the update rule, yielding equally tight theoretical results. Comprehensive experiments on convex benchmarks and deep neural networks corroborate our theory: the proposed step size achieves competitive performance to existing adaptive baselines and exhibits stable behavior across a wide range of problem settings. Finally, in the context of deep neural network training, the gradient norms under our step size do not collapse to (near) zero, indicating robustness to vanishing gradients.

Optimization · Non-Convex

Foivos Alimisis, Rustem Islamov, Aurelien Lucchi

Learning rate warm-up -- increasing the learning rate at the beginning of training -- has become a ubiquitous heuristic in modern deep learning, yet its theoretical foundations remain poorly understood. In this work, we provide a principled explanation for why warm-up improves training. We rely on a generalization of the $(L_0, L_1)$-smoothness condition, which bounds local curvature as a linear function of the loss sub-optimality and exhibits desirable closure properties. We show -- both theoretically and empirically -- that this condition is satisfied by common neural architectures and accurately captures the curvature of the optimization landscape early in training. Adapting the learning rate in response to this curvature condition naturally induces a warm-up–like schedule, and we show that this choice yields provably faster convergence guarantees than using a fixed learning rate. Finally, we validate our theoretical insights through experiments on language and vision models, confirming the agreement between our theoretically derived schedule and standard warm-up.

Optimization · Discrete and Combinatorial Optimization

Wenzheng Pan, Jiale Ma, Nuoyan Chen, Yang Li, Junchi Yan

Despite the fast progress of Neural Combinatorial Optimization (NCO) on graphs, existing solvers mainly learn a narrow task (e.g., uniform TSP) at a time and hardly handle instances over diverse distributions. This paper proposes M$^2$GenCO, a Multi-task learning framework that pioneers the instantiation of the Meta-learning mechanism with diffusion-based Generative solving for CO Problems (COPs) on graphs, first formulating "tasks" in meta-learning as distinct problem types instead of instances of the same problem. With a tailored lightweight graph neural network, our framework performs effective joint pre-training on a variety of problem types and efficient fine-tuning to adapt for out-of-distribution scenarios. Further, we establish a benchmark comprising 5 classic graph COPs with varying scales and multiple distributions, forming 38 distinct test datasets that facilitate standard evaluation of generalizability and adaptability for NCO solvers. Empirically, M$^2$GenCO with greedy decoder yields an overall 9.16% performance gain with an average 95.6$\times$ acceleration for inference, and achieves concrete state-of-the-arts on all test sets with simple local searchers, maintaining superior solving time against previous neural methods. The computational resource and time consumption for training are saved by up to 82% and 91%, respectively.

Deep Learning · Everything Else

Yinghao Ma, Haiwen Xia, Hewei Gao, Weixiong Chen, Ye Yuxin, Yuchen Yang, Sungkyun Chang, Mingshuo Ding, Yizhi Li, Ruibin Yuan 等

While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind, remaining fragmented and narrowly focused. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for Compositional Music Instruction (CMI) reward modeling, where the generated music may be conditioned on text descriptions, lyrics, and/or audio prompts. We first introduce CMIPref-Pseudo, a large-scale preference dataset comprising 110k pseudo-labeled samples, and CMI-Pref, a high-quality, human-annotated corpus tailored for fine-grained alignment tasks. To unify the evaluation landscape, we propose CMIRewardBench, a unified benchmark that evaluates music reward models on heterogeneous samples across musicality, text–music alignment, and compositional instruction alignment. Leveraging these resources, we develop CMI reward models (CMI-RMs), a parameter-efficient reward model family capable of processing heterogeneous inputs. We evaluate their correlation with human judgments scores on Music Arena and CMI-Pref test set, as well as preference agreement on Music Arena and CMI-Pref. Additional analyses examine performance variation across factors such as annotators, annotation timing and confidence, music generation models, and audio length. Experiments demonstrate that CMI-RM not only correlates strongly with human judgments, but also enables effective inference-time scaling via topk filtering. Our work provides the necessary data, benchmarks, and models to advance aligned music generation.