论文检索

Deep Learning · Foundation Models

Wujian Peng, Lingchen Meng, Yuxuan Cai, Xianwei Zhuang, Yuhuan Yang, Rongyao Fang, Chenfei Wu, Junyang Lin, Zuxuan Wu, Shuai Bai

Unified Multimodal Modeling aims to integrate visual understanding and generation within a single system. However, existing approaches typically rely on two disparate visual tokenizers, which splits the representation space and hinder truly unified modeling. We propose UniAR, a unified autoregressive framework where a single discrete visual tokenizer serves as the key bridge between understanding and generation, enabling a shared context in which the model can directly interpret its own generated visual tokens without additional re-encoding. UniAR adapts a pretrained vision encoder with multi-level feature fusion and a lookup-free bitwise quantization scheme, preserving both high-level semantics and low-level details while scaling the effective visual vocabulary at minimal cost. Building on this, the unified autoregressive model adopts parallel-bitwise-prediction to jointly predict spatially grouped, multi-level visual codes, substantially reducing visual sequence length and accelerating generation. Finally, a diffusion-based visual decoder operates on discrete visual tokens to reconstruct high-fidelity images. Through large-scale pre-training on 1T multimodal tokens, followed by supervised fine-tuning and reinforcement learning, UniAR achieves state-of-the-art performance on text-to-image generation and image editing while remaining competitive on multimodal understanding benchmarks.

General Machine Learning · Representation Learning

yan wubin, Wei Ma, Shixiang Wan, Dongchen Li, Shaoshun Kang, Qing Yang, Dongliang Xu

Connectionist models and symbolic models have long embodied two divergent paradigms: the former excel at differentiable representation learning yet struggle with transparency, while the latter deliver explicit rule-based reasoning but resist gradient-based optimization. We introduce Arboreal Neural Networks (ArbNN), a neural–symbolic framework that unifies these paradigms both computationally and conceptually. At the design level, ArbNN departs fundamentally from prior neuralized-tree models through a depth-aware routing mechanism and a topology-informed softmax aggregation, which together enable one-shot full-path gradient propagation and consequently achieving rapid and well-conditioned optimization dynamics and high parallel inference efficiency. At the conceptual level, ArbNN reveals that decision-tree branching and self-attention routing are two realizations of the same conditional computation primitive. We prove a structural isomorphism between a decision tree and a single-query attention head, enabling a differentiable architecture that faithfully preserves symbolic decision logic. The defining property of ArbNN is Bidirectional Fidelity, ensuring that the neural module can be compiled from—and losslessly decompiled back into—a symbolic tree, yielding both ordering consistency in ranking behavior and explicit, auditable interpretability via reconstructed if–else rules. ArbNN further supports GBDT-based initialization, allowing it to inherit strong inductive biases and integrate seamlessly with existing production workflows. Empirically, ArbNN achieves state-of-the-art performance on various public tabular benchmarks and delivers consistent gains under temporal distribution shift in large-scale industrial credit-risk systems. To support realistic evaluation, we additionally contribute TabCredit, a feature-rich, temporally partitioned dataset built from millions of real-world loan applications. Together, these results demonstrate that ArbNN forms a unified, reversible, and practically deployable bridge between symbolic reasoning and neural computation for high-stakes tabular domains.

Deep Learning · Generative Models and Autoencoders

Walter Nelson, Theofanis Karaletsos, Francesco Locatello

Recently, sparse autoencoders (SAEs) have emerged as an attractive tool for interpreting and interacting with representations in practical neural networks. While it is common empirical folklore, we also show theoretically that SAEs are highly unstable: different training runs are likely to produce different concept dictionaries and sparse codes. We characterize the model characteristics that get in the way of the stability of real-world SAEs, and address each of these problems through minimal changes to the architecture and training procedure. Together, these changes yield iSAE, a variant of the standard TopK SAE with lower reconstruction error and improved stability. We explain this improvement theoretically by connecting SAEs with traditional dictionary learning approaches, and show that the dictionaries learned in practice satisfy an approximate restricted isometry condition, rendering the corresponding sparse codes in those models near-identifiable.

Social Aspects · Accountability, Transparency, and Interpretability

Millicent Li, Alberto Mario Ceballos Arroyo, Giordano Rogers, Naomi Saphra, Byron Wallace

Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verbalizer LLM. This is intended to illuminate how the target model represents and operates on inputs. But do such activation verbalization approaches actually provide privileged knowledge about the internal workings of the target model, or do they merely convey information about its inputs? We critically evaluate popular verbalization methods across datasets used in prior work and find that they can succeed at benchmarks without any access to target model internals, suggesting that these datasets may not be ideal for evaluating verbalization methods. We then run controlled experiments which reveal that verbalizations often reflect the parametric knowledge of the verbalizer LLM which generated them, rather than the knowledge of the target LLM whose activations are decoded. Taken together, our results indicate a need for targeted benchmarks and experimental controls to rigorously assess whether verbalization methods provide meaningful insights into the operations of LLMs.

Applications · Computer Vision

Xueqiang Lv, Shizhou Zhang, Yinghui Xing, di xu, Peng Wang, Yanning Zhang

Open-world object detection (OWOD) requires incrementally detecting known categories while reliably identifying unknown objects. Existing methods primarily focus on improving unknown recall, yet overlook interpretability, often leading to known–unknown confusion and reduced prediction reliability. This paper aims to make the entire OWOD framework interpretable, enabling the detector to truly “knowing the unknown.” To this end, we propose a concept-driven InterPretable OWOD framework(IPOW) by introducing a Concept Decomposition Model (CDM) for OWOD, which explicitly decomposes the coupled RoI features in Faster R-CNN into discriminative, shared, and background concepts. Discriminative concepts identify the most discriminative features to enlarge the distances between known categories, while shared and background concepts, due to their strong generalization ability, can be readily transferred to detect unknown categories. Leveraging the interpretable framework, we identify that known–unknown confusion arises when unknown objects fall into the discriminative space of known classes. To address this, we propose Concept-Guided Rectification (CGR) to further resolve such confusion. Extensive experiments show that IPOW significantly improves unknown recall while mitigating confusion, and provides concept-level interpretability for both known and unknown predictions.

Deep Learning · Robustness

Jiaqi Tang, Jianmin Chen, Youyang Zhai, Wei Wei, Runtao Liu, Mengjie Zhao, Xiangyu Wu, Qingfa Xiao, Qifeng Chen

Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions. While existing robustness enhancement approaches exist, they are limited: black-box feature alignment lacks interpretability, and white-box text-based reasoning cannot restore lost pixel-level details. This work investigates a fundamental research question: Can MLLMs recover corrupted visual content by themselves? To address this, we propose Robust-U1, a novel framework that equips MLLMs with explicit visual self-recovery capability for robust understanding. The approach comprises three core stages: supervised fine-tuning for initial reconstruction, reinforcement learning with dual rewards (pixel-level SSIM and semantic-level CLIP similarity) for aligning high visual quality, and multimodal reasoning that jointly considers both the corrupted input and the recovered image. Extensive experiments demonstrate that Robust-U1 achieves state-of-the-art robustness on the real-world corruption benchmark (R-Bench) and maintains superior performance under adversarial corruptions on general VQA benchmarks (MMMB, MMStar, RealWorldQA). Analysis confirms that high-quality visual recovery directly enhances reasoning performance, establishing self-recovery as a critical mechanism for robust visual understanding. Code, demo, and models will be open-sourced soon.

Social Aspects · Safety

Joonhyuk Baek, Wonjune Seo, Jae-yun Kim, Saerom Park, Hoki Kim

Despite the proliferation of proactive defenses against deepfakes, the lack of a unified evaluation protocol precludes fair comparison and masks critical vulnerabilities. To bridge this gap, we present the first comprehensive benchmark that systematically assesses disruption, robustness, and transferability encompassing pixel, perceptual, and identity metrics. Our extensive analysis reveals that fidelity and identity metrics capture orthogonal performance axes, often leading to conflicting interpretations when relied upon individually. Furthermore, we identify a fundamental trade-off where peak white-box performance signals overfitting, and we introduce a calibrated evaluation to correct generator-induced identity bias. By exposing these blind spots, we establish a rigorous standard to guide the development of genuinely generalizable protections.

Social Aspects · Accountability, Transparency, and Interpretability

Ziming Mao, Jia Xu, Wenxuan Pan, Mufan Xue, Yaochu Jin, Guoyuan Yang

Understanding the internal mechanisms of Deep Neural Networks remains a significant challenge, particularly in elucidating how generic visual concepts emerge within latent spaces. In this work, we propose SAEs-BrainMap, a novel framework that utilizes human brain activation patterns from the ventral visual pathway as objective probes to guide the identification of features decomposed by Sparse Autoencoders (SAEs). Our quantitative and qualitative empirical results demonstrate a robust representational alignment between sparse model features and biological Regions of Interest (ROIs), confirming the feasibility of utilizing brain signals to characterize model functionality. By leveraging this alignment, we trace the hierarchical trajectory of generic concepts cross layers and utilize the brain's hierarchical structure to visualize the model's global processing flow, providing novel insights into model interpretability.

Deep Learning · Large Language Models

Frédéric Berdoz, Luca Lanzendörfer, René Caky, Roger Wattenhofer

Alignment of large language models remains a central challenge in natural language processing. Preference optimization has emerged as a popular and effective method for improving alignment, typically through training-time or prompt-based interventions. In this paper, we introduce alignment-aware decoding (AAD), a method to enhance model alignment directly at inference. Theoretically, AAD can be interpreted as implicit reward optimization, yet it requires no specialized training beyond the standard DPO setup. Empirically, AAD consistently outperforms strong baselines across diverse alignment benchmarks and model scales. Moreover, in data-constrained settings, AAD can produce high-quality synthetic data to improve alignment under standard decoding, providing a practical solution when labeled data is limited.

Deep Learning · Large Language Models

Hong-Yu Chen, Po-Chiao Lin, Maojiang Su, Jerry Yao-Chieh Hu, Han Liu

We study the in-context universal approximation and compositional generalization of softmax Transformers. We prove an in-context universality result: a fixed-weight softmax Transformer approximates a broad class of continuous sequence-to-sequence functions. Building on this universality, we establish a composition theorem: by concatenating prompts associated with simple ``subprograms,'' the same fixed Transformer executes their composition, and thereby synthesizes more complex programs on-the-fly. These results support a principled view of prompts as programs and fixed-weight Transformers as program interpreters. Moreover, we provide a concrete mechanism by which GPT-style models both execute and assemble algorithms in context.

Social Aspects · Accountability, Transparency, and Interpretability

Pierre Fernandez, Tom Sander, Hady Elsahar, Hongyan Chang, Tomáš Souček, Valeriu Lacatusu, Tuan Tran, Sylvestre-Alvise Rebuffi, Alexandre Mourachko

Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore post-hoc watermarking where an LLM rewrites existing text while applying generation-time watermarking, to protect copyrighted documents, or detect their use in training or RAG via watermark radioactivity. Unlike generation-time approaches which are constrained by how LLMs are served, this setting offers additional degrees of freedom for both generation and detection. We thus investigate how allocating compute (through larger rephrasing models, beam search, multi-candidate generation, or entropy filtering at detection) affects the quality-detectability trade-off. Among our findings, the simple Gumbel-max scheme surprisingly outperforms more recent alternatives under nucleus sampling, and achieves strong detectability and semantic fidelity on open-ended text such as books. Moreover, most methods benefit significantly from beam search, and we counterintuitively find that smaller models outperform larger ones. However, our solutions struggles when watermarking verifiable text such as code. This study reveals both the potential and limitations of post-hoc watermarking, laying groundwork for practical applications and future research.

Social Aspects · Accountability, Transparency, and Interpretability

Sylvestre-Alvise Rebuffi, Tuan Tran, Valeriu Lacatusu, Pierre Fernandez, Tomáš Souček, Nikola Jovanović, Tom Sander, Hady Elsahar, Alexandre Mourachko

Existing approaches for watermarking AI-generated images often rely on post-hoc methods applied in pixel space, introducing computational overhead and potential visual artifacts. In this work, we explore latent space watermarking and introduce DistSeal, a unified approach for latent watermarking that works across both diffusion and autoregressive models. Our approach works by training post-hoc watermarking models in the latent space of generative models. We demonstrate that these latent watermarkers can be effectively distilled either into the generative model itself or into the latent decoder, enabling in-model watermarking. The resulting latent watermarks achieve competitive robustness while offering similar imperceptibility and up to 20x speedup compared to pixel-space baselines. Our experiments further reveal that distilling latent watermarkers outperforms distilling pixel-space ones, providing a solution that is both more efficient and more robust.

Deep Learning · Sequential Models, Time series

Luke Thompson, Dai Shi, Lequan Lin, Junbin Gao, Andi Han

Neural rough differential equations (NRDEs) learn continuous-time dynamics from irregularly sampled sequences by encoding the input path with signature features, providing robustness to discretisation and sampling irregularity. However, existing NRDEs implicitly rely on algebraic identities that can fail in two important settings: *stochastic dynamics* interpreted in the Itô sense, and *dynamics evolving on manifolds* where curvature renders the effect of repeated derivatives order-dependent. In this work, we propose Branched Neural Rough Differential Equations (B-NRDEs), a unified framework that replaces geometric signature features with tree-based (branched) rough-path lifts, yielding models that remain well-defined under Itô noise and on manifolds. Building on these branched lifts, an Itô-consistent training objective is introduced via the branched signature kernel. We provide an efficient, autodifferentiable package *Stochastax* for computing branched (log-)signatures and solving (manifold) RDEs. Across various applications, including rough Bergomi volatility modelling, sim-to-real $\mathrm{SO}(3)$ dynamics forecasting, and SPD covariance dynamics, B-NRDE shows consistently strong results.

Deep Learning · Large Language Models

Valentin NOËL

Validating mathematical reasoning in large language models currently requires a trade-off between computationally expensive learned verifiers and the unreliability of output-based heuristics. We therefore propose a training-free, mechanistic alternative: spectral analysis of attention topology. By treating attention matrices as dynamic graphs over tokens, we extract four interpretable spectral diagnostics, Fiedler value, High-Frequency Energy Ratio (HFER), spectral entropy, and graph smoothness, that differentiate valid reasoning from hallucinated outputs without any learned parameters. We perform experiments across seven models from four architectural families (Llama, Qwen, Phi, Mistral) yield effect sizes up to Cohen's $d = 3.30$ ($p < 10^{-116}$), enabling $85$--$96\%$ classification accuracy with a single threshold. We discover that spectral analysis detects logical coherence rather than compiler acceptance: proofs rejected by formal verifiers due to timeouts or missing imports are correctly identified as valid, a phenomenon we term "Platonic validity". Furthermore, causal ablation studies confirm that this spectral signature reflects the functional health of induction head circuits, establishing a mechanistic basis for the method. We also identify an architectural dependency: Sliding Window Attention shifts the discriminative signal from HFER to late-layer smoothness ($d = 2.09$, $p < 10^{-48}$), demonstrating that attention mechanism design determines which spectral features capture reasoning validity. The method generalizes to informal chain-of-thought reasoning ($d = 0.78$, $p < 10^{-3}$). These findings establish spectral graph analysis as a principled framework for reasoning verification, with immediate applications to hallucination detection and real-time safety monitoring.

Social Aspects · Safety

Enrico Cassano, Riccardo Renzulli, Marco Nurisso, Mirko Zaffaroni, Alan Perotti, Marco Grangetto

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse autoencoder framework that overcomes this by enforcing one-to-one concept-neuron mappings. By systematically labeling concepts during training, our method achieves feature centralization, binding each concept to a single, interpretable neuron. This enables highly targeted and efficient concept erasure. SAEmnesia reduces hyperparameter search by 96.7% and achieves a 9.2% improvement over the state-of-the-art on the UnlearnCanvas benchmark. Our method also demonstrates superior scalability in sequential unlearning, improving accuracy by 28.4% when removing nine objects, establishing a new standard for precise and controllable concept erasure. Moreover, SAEmnesia mitigates the possibility of generating unwanted content under adversarial attack and effectively removes nudity when evaluated with I2P.

Social Aspects · Accountability, Transparency, and Interpretability

Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice, Arianna Casanova, Francesco Giannini, Michelangelo Diligenti, Mateo Espinosa Zarlenga, Pietro Barbiero, Johannes Schneider, Danilo Giordano

Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically fix their task predictor to a single linear or Boolean expression, limiting both predictive accuracy and adaptability to diverse user needs. We propose Mixture of Concept Bottleneck Experts (M-CBEs), a framework that generalizes existing CBMs along two dimensions: the number of experts and the functional form of each expert, exposing an underexplored region of the design space. We investigate this region by instantiating two novel models: Linear M-CBE, which learns a finite set of linear expressions, and Symbolic M-CBE, which leverages symbolic regression to discover expert functions from data under user-specified operator vocabularies. Empirical evaluation demonstrates that varying the mixture size and functional form provides a robust framework for navigating the accuracy-interpretability trade-off, adapting to different user and task needs.

Social Aspects · Accountability, Transparency, and Interpretability

Stefano Colamonaco, David Debot, Pietro Barbiero, Giuseppe Marra

Concept Bottleneck Models (CBMs) aim to improve interpretability by mediating predictions through human-understandable concepts, but they provide no way to verify whether learned concepts align with the human's intended meaning, hurting interpretability. We introduce Prototype-Grounded Concept Models (PGCMs), which ground concepts in learned visual prototypes: image parts that serve as explicit evidence for the concepts. This grounding enables direct inspection of concept semantics and supports targeted human intervention at the prototype level to correct misalignments. Empirically, PGCMs match the predictive performance of state-of-the-art CBMs while substantially improving transparency, interpretability, and intervenability.

Deep Learning · Large Language Models

Jianhui Chen, Yuzhang Luo, Liangming Pan

Mechanistic Interpretability has successfully identified functional circuits in Large Language Models (LLMs), yet their causal origins in the training data remain poorly understood. We bridge this gap by introducing **Mechanistic Data Attribution (MDA)**, a scalable framework that traces the formation of specific interpretable units back to training samples using Influence Functions. Through extensive pre-training experiments on the Pythia family, we causally validate that removing a small fraction of high-influence samples significantly hinders the emergence of targeted heads, whereas augmenting them accelerates formation—effects that random interventions fail to replicate. Leveraging MDA, we reveal that highly repetitive structural data—such as LaTeX and HTML—acts as a "catalyst" that significantly accelerates the emergence of induction heads. Furthermore, we observe that interventions targeting induction head formation induce a concurrent change in the model’s in-context learning (ICL) capability. This provides direct causal evidence for the long-standing hypothesis regarding the functional link between induction heads and ICL. Finally, we propose a mechanistic data augmentation pipeline that builds upon these insights to consistently accelerate mechanistic convergence across diverse model scales, offering a principled methodology for understanding and steering the fine-grained development of LLM behaviors.

General Machine Learning · Causality

Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Schölkopf, Mario Fritz

As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), is increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously, especially while preserving utility. This position paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI. We ground our arguments in re-interpreting trustworthy AI trade-offs as incompatible invariance requirements under different changes to the data-generating process. We then illustrate that causality provides a unifying framework for understanding how trade-offs in trustworthy AI arise, and how they can be softened or resolved through selective invariance. This perspective applies to both classical ML models and large-scale FMs. Our paper discusses how causal assumptions may be applied explicitly or implicitly in modern large-scale systems. Finally, we outline open challenges and opportunities for using causality to build more trustworthy AI.

Sobhan Lotfi, Ava Iranmanesh, Lachin Naghashyar, Ali Shirali, Fateme Haredasht, Sanmi Koyejo, Phil Torr, Yong Suk Lee, Fazl Barez, Joel Lehman 等

Breakthroughs often come from ideas we could not have predicted in advance. In biology, this is called exaptation: traits evolved for one function become decisive for another. Scientific progress works similarly, but only if ideas survive periods when they appear uncompetitive by current metrics. This position paper argues that AI's benchmark-centered selection environment, while successful at bypassing complex debates about the nature of intelligence, taxes exaptation. When one selection rule dominates, ideas that do not fit it have nowhere to persist. The cost grows acute as the field shifts from asking can machines exhibit intelligent behavior? to asking can machines exhibit intelligent behavior such that they are aligned, interpretable, and safe? These are philosophically distinct questions that may require discoveries that we cannot specify. We propose mechanisms to restore exaptive capacity without abandoning benchmarking: plural evaluation regimes, protected venues for non-comparable work, long-horizon funding, and training norms that encourage researchers to question selection rules, not only optimize within them.