arXiv subjects

Matthias Bethge

Publications and source records attributed to Matthias Bethge.

At least 37 records · Page 2Linked to original sources

arXiv2025

Solving Spatial Supersensing Without Spatial Supersensing

Cambrian-S aims to take the first steps towards improving video world models with spatial supersensing by introducing (i) two benchmarks, VSI-Super-Recall (VSR) and VSI-Super-Counting (VSC), and (ii) bespoke predictive sensing inference strategies tailored to each benchmark. In this work, we conduct a critical analysis of Cambrian-S across both these fronts. First, we introduce a simple baseline, NoSense, which discards almost all temporal structure and uses only a bag-of-words SigLIP model, yet near-perfectly solves VSR, achieving 95% accuracy even on 4-hour videos. This shows benchmarks like VSR can be nearly solved without spatial cognition, world modeling or spatial supersensing. Second, we hypothesize that the tailored inference methods proposed by Cambrian-S likely exploit shortcut heuristics in the benchmark. We illustrate this with a simple sanity check on the VSC benchmark, called VSC-Repeat: We concatenate each video with itself 1-5 times, which does not change the number of unique objects. However, this simple perturbation entirely collapses the mean relative accuracy of Cambrian-S from 42% to 0%. A system that performs spatial supersensing and integrates information across experiences should recognize views of the same scene and keep object-count predictions unchanged; instead, Cambrian-S inference algorithm relies largely on a shortcut in the VSC benchmark that rooms are never revisited. Taken together, our findings suggest that (i) current VSI-Super benchmarks do not yet reliably measure spatial supersensing, and (ii) predictive-sensing inference recipes used by Cambrian-S improve performance by inadvertently exploiting shortcuts rather than from robust spatial supersensing. We include the response from the Cambrian-S authors (in Appendix A) to provide a balanced perspective alongside our claims. We release our code at: https://github.com/bethgelab/supersanity

cs.CV↗

arXiv2025

AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?

Despite progress in language model (LM) capabilities, evaluations have thus far focused on models' performance on tasks that humans have previously solved, including in programming (Jimenez et al., 2024) and mathematics (Glazer et al., 2024). We therefore propose testing models' ability to design and implement algorithms in an open-ended benchmark: We task LMs with writing code that efficiently solves computationally challenging problems in computer science, physics, and mathematics. Our AlgoTune benchmark consists of 154 coding tasks collected from domain experts and a framework for validating and timing LM-synthesized solution code, which is compared to reference implementations from popular open-source packages. In addition, we develop a baseline LM agent, AlgoTuner, and evaluate its performance across a suite of frontier models. AlgoTuner uses a simple, budgeted loop that edits code, compiles and runs it, profiles performance, verifies correctness on tests, and selects the fastest valid version. AlgoTuner achieves an average 1.72x speedup against our reference solvers, which use libraries such as SciPy, sk-learn and CVXPY. However, we find that current models fail to discover algorithmic innovations, instead preferring surface-level optimizations. We hope that AlgoTune catalyzes the development of LM agents exhibiting creative problem solving beyond state-of-the-art human performance.

cs.SE↗

arXiv2025

Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions

We propose Equivariance by Contrast (EbC) to learn equivariant embeddings from observation pairs $(\mathbf{y}, g \cdot \mathbf{y})$, where $g$ is drawn from a finite group acting on the data. Our method jointly learns a latent space and a group representation in which group actions correspond to invertible linear maps -- without relying on group-specific inductive biases. We validate our approach on the infinite dSprites dataset with structured transformations defined by the finite group $G:= (R_m \times \mathbb{Z}_n \times \mathbb{Z}_n)$, combining discrete rotations and periodic translations. The resulting embeddings exhibit high-fidelity equivariance, with group operations faithfully reproduced in latent space. On synthetic data, we further validate the approach on the non-abelian orthogonal group $O(n)$ and the general linear group $GL(n)$. We also provide a theoretical proof for identifiability. While broad evaluation across diverse group types on real-world data remains future work, our results constitute the first successful demonstration of general-purpose encoder-only equivariant learning from group action observations alone, including non-trivial non-abelian groups and a product group motivated by modeling affine equivariances in computer vision.

cs.LG↗

arXiv2025

Mapping Post-Training Forgetting in Language Models at Scale

Scaled post-training now drives many of the largest capability gains in language models (LMs), yet its effect on pretrained knowledge remains poorly understood. Not all forgetting is equal: Forgetting one fact (e.g., a U.S. president or an API call) does not "average out" by recalling another. Hence, we propose a sample-wise paradigm to measure what is forgotten and when backward transfer occurs. Our metric counts 1->0 transitions (correct before post-training, incorrect after) to quantify forgetting and 0->1 transitions to quantify backward transfer. Traditional task averages conflate these effects and obscure large changes. For multiple-choice benchmarks, we add chance-adjusted variants that subtract the expected contribution of random guessing from pre- and post-training accuracies. We apply this framework across post-training stages, model sizes, and data scales. Our large-scale analysis shows that: (1) Domain-continual pretraining induces moderate forgetting with low-to-moderate backward transfer; (2) RL/SFT post-training applied to base models and Instruction tuning yields moderate-to-large backward transfer on math and logic with overall low-to-moderate forgetting; (3) Applying RL/SFT to instruction-tuned models is sensitive on data scale: at small scales, both forgetting and backward transfer are small; at larger scales, effects are mixed and warrant further study with better controls; (4) Model merging does not reliably mitigate forgetting. Overall, our framework offers a practical yardstick for mapping how post-training alters pretrained knowledge at scale -- enabling progress towards generally capable AI systems.

cs.LG↗

arXiv2025

A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility

Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces methodological rigor, with many evaluations relying on benchmarking practices that lack transparency, robustness, or statistical grounding. In this work, we conduct a comprehensive empirical study and find that current mathematical reasoning benchmarks are highly sensitive to subtle implementation choices--including decoding parameters, random seeds, prompt formatting, and even hardware and software configurations. Performance gains reported in recent studies frequently hinge on unclear comparisons or unreported sources of variance. To address these issues, we propose a standardized evaluation framework with clearly defined best practices and reporting standards. Using this framework, we reassess recent methods and find that most reinforcement learning (RL) approaches yield only modest improvements--far below prior claims--and are prone to overfitting, especially on small-scale benchmarks like AIME'24. In contrast, supervised finetuning (SFT) methods show consistently stronger generalization in the settings we study. To foster reproducibility, we release all code, prompts, and model outputs, for reasoning benchmarks, establishing more rigorous foundations for future work.

cs.LG↗

arXiv2025

Modeling Saliency Dataset Bias

Recent advances in image-based saliency prediction are approaching gold standard performance levels on existing benchmarks. Despite this success, we show that predicting fixations across multiple saliency datasets remains challenging due to dataset bias. We find a significant performance drop (around 40%) when models trained on one dataset are applied to another. Surprisingly, increasing dataset diversity does not resolve this inter-dataset gap, with close to 60% attributed to dataset-specific biases. To address this remaining generalization gap, we propose a novel architecture extending a mostly dataset-agnostic encoder-decoder structure with fewer than 20 dataset-specific parameters that govern interpretable mechanisms such as multi-scale structure, center bias, and fixation spread. Adapting only these parameters to new data accounts for more than 75% of the generalization gap, with a large fraction of the improvement achieved with as few as 50 samples. Our model sets a new state-of-the-art on all three datasets of the MIT/Tuebingen Saliency Benchmark (MIT300, CAT2000, and COCO-Freeview), even when purely generalizing from unrelated datasets, but with a substantial boost when adapting to the respective training datasets. The model also provides valuable insights into spatial saliency properties, revealing complex multi-scale effects that combine both absolute and relative sizes.

cs.CV↗

arXiv2025

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs

Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrificing helpfulness. We show that frontier LLMs can develop a preference for dishonesty as a new strategy, even when other options are available. Affected models respond to harmful requests with outputs that sound harmful but are crafted to be subtly incorrect or otherwise harmless in practice. This behavior emerges with hard-to-predict variations even within models from the same model family. We find no apparent cause for the propensity to deceive, but show that more capable models are better at executing this strategy. Strategic dishonesty already has a practical impact on safety evaluations, as we show that dishonest responses fool all output-based monitors used to detect jailbreaks that we test, rendering benchmark scores unreliable. Further, strategic dishonesty can act like a honeypot against malicious users, which noticeably obfuscates prior jailbreak attacks. While output monitors fail, we show that linear probes on internal activations can be used to reliably detect strategic dishonesty. We validate probes on datasets with verifiable outcomes and by using them as steering vectors. Overall, we consider strategic dishonesty as a concrete example of a broader concern that alignment of LLMs is hard to control, especially when helpfulness and harmlessness conflict.

cs.LG↗

arXiv2025

Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models

With the advent and recent ubiquity of foundation models, continual learning (CL) has recently shifted from continual training from scratch to the continual adaptation of pretrained models, seeing particular success on rehearsal-free CL benchmarks (RFCL). To achieve this, most proposed methods adapt and restructure parameter-efficient finetuning techniques (PEFT) to suit the continual nature of the problem. Based most often on input-conditional query-mechanisms or regularizations on top of prompt- or adapter-based PEFT, these PEFT-style RFCL (P-RFCL) approaches report peak performances; often convincingly outperforming existing CL techniques. However, on the other end, critical studies have recently highlighted competitive results by training on just the first task or via simple non-parametric baselines. Consequently, questions arise about the relationship between methodological choices in P-RFCL and their reported high benchmark scores. In this work, we tackle these questions to better understand the true drivers behind strong P-RFCL performances, their placement w.r.t. recent first-task adaptation studies, and their relation to preceding CL standards such as EWC or SI. In particular, we show: (1) P-RFCL techniques relying on input-conditional query mechanisms work not because, but rather despite them by collapsing towards standard PEFT shortcut solutions. (2) Indeed, we show how most often, P-RFCL techniques can be matched by a simple and lightweight PEFT baseline. (3) Using this baseline, we identify the implicit bound on tunable parameters when deriving RFCL approaches from PEFT methods as a potential denominator behind P-RFCL efficacy. Finally, we (4) better disentangle continual versus first-task adaptation, and (5) motivate standard RFCL techniques s.a. EWC or SI in light of recent P-RFCL methods.

cs.LG↗

arXiv2025

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

Keeping large language models factually up-to-date is crucial for deployment, yet costly retraining remains a challenge. Knowledge editing offers a promising alternative, but methods are only tested on small-scale or synthetic edit benchmarks. In this work, we aim to bridge research into lifelong knowledge editing to real-world edits at a practically relevant scale. We first introduce WikiBigEdit; a large-scale benchmark of real-world Wikidata edits, built to automatically extend lifelong for future-proof benchmarking. In its first instance, it includes over 500K question-answer pairs for knowledge editing alongside a comprehensive evaluation pipeline. Finally, we use WikiBigEdit to study existing knowledge editing techniques' ability to incorporate large volumes of real-world facts and contrast their capabilities to generic modification techniques such as retrieval augmentation and continual finetuning to acquire a complete picture of the practical extent of current lifelong knowledge editing.

cs.CL↗

arXiv2025

ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities

Traditional fixed test sets fall short in evaluating open-ended capabilities of foundation models. To address this, we propose ONEBench(OpeN-Ended Benchmarking), a new testing paradigm that consolidates individual evaluation datasets into a unified, ever-expanding sample pool. ONEBench allows users to generate custom, open-ended evaluation benchmarks from this pool, corresponding to specific capabilities of interest. By aggregating samples across test sets, ONEBench enables the assessment of diverse capabilities beyond those covered by the original test sets, while mitigating overfitting and dataset bias. Most importantly, it frames model evaluation as a collective process of selecting and aggregating sample-level tests. The shift from task-specific benchmarks to ONEBench introduces two challenges: (1)heterogeneity and (2)incompleteness. Heterogeneity refers to the aggregation over diverse metrics, while incompleteness describes comparing models evaluated on different data subsets. To address these challenges, we explore algorithms to aggregate sparse measurements into reliable model scores. Our aggregation algorithm ensures identifiability(asymptotically recovering ground-truth scores) and rapid convergence, enabling accurate model ranking with less data. On homogenous datasets, we show our aggregation algorithm provides rankings that highly correlate with those produced by average scores. We also demonstrate robustness to ~95% of measurements missing, reducing evaluation cost by up to 20x with little-to-no change in model rankings. We introduce ONEBench-LLM for language models and ONEBench-LMM for vision-language models, unifying evaluations across these domains. Overall, we present a technique for open-ended evaluation, which can aggregate over incomplete, heterogeneous sample-level measurements to continually grow a benchmark alongside the rapidly developing foundation models.

cs.LG↗

arXiv2025

Great Models Think Alike and this Undermines AI Oversight

As Language Model (LM) capabilities advance, evaluating and supervising them at scale is getting harder for humans. There is hope that other language models can automate both these tasks, which we refer to as ''AI Oversight''. We study how model similarity affects both aspects of AI oversight by proposing Chance Adjusted Probabilistic Agreement (CAPA): a metric for LM similarity based on overlap in model mistakes. Using CAPA, we first show that LLM-as-a-judge scores favor models similar to the judge, generalizing recent self-preference results. Then, we study training on LM annotations, and find complementary knowledge between the weak supervisor and strong student model plays a crucial role in gains from ''weak-to-strong generalization''. As model capabilities increase, it becomes harder to find their mistakes, and we might defer more to AI oversight. However, we observe a concerning trend -- model mistakes are becoming more similar with increasing capabilities, pointing to risks from correlated failures. Our work underscores the importance of reporting and correcting for model similarity, especially in the emerging paradigm of AI oversight.

cs.LG↗

arXiv2025

A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks

We investigate 17 benchmarks (e.g. SugarCREPE, VALSE) commonly used for measuring compositional understanding capabilities of vision-language models (VLMs). We scrutinize design choices in their construction, including data source (e.g. MS-COCO) and curation procedures (e.g. constructing negative images/captions), uncovering several inherent biases across most benchmarks. We find that blind heuristics (e.g. token-length, log-likelihood under a language model) perform on par with CLIP models, indicating that these benchmarks do not effectively measure compositional understanding. We demonstrate that the underlying factor is a distribution asymmetry between positive and negative images/captions, induced by the benchmark construction procedures. To mitigate these issues, we provide a few key recommendations for constructing more robust vision-language compositional understanding benchmarks, that would be less prone to such simple attacks.

cs.CV↗

arXiv2025

In Search of Forgotten Domain Generalization

Out-of-Domain (OOD) generalization is the ability of a model trained on one or more domains to generalize to unseen domains. In the ImageNet era of computer vision, evaluation sets for measuring a model's OOD performance were designed to be strictly OOD with respect to style. However, the emergence of foundation models and expansive web-scale datasets has obfuscated this evaluation process, as datasets cover a broad range of domains and risk test domain contamination. In search of the forgotten domain generalization, we create large-scale datasets subsampled from LAION -- LAION-Natural and LAION-Rendition -- that are strictly OOD to corresponding ImageNet and DomainNet test sets in terms of style. Training CLIP models on these datasets reveals that a significant portion of their performance is explained by in-domain examples. This indicates that the OOD generalization challenges from the ImageNet era still prevail and that training on web-scale data merely creates the illusion of OOD generalization. Furthermore, through a systematic exploration of combining natural and rendition datasets in varying proportions, we identify optimal mixing ratios for model generalization across these domains. Our datasets and results re-enable meaningful assessment of OOD robustness at scale -- a crucial prerequisite for improving model robustness.

cs.CV↗

arXiv2025

Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models

Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual stimuli and human judgments on visual cognition tasks, allowing us to systematically evaluate performance across cognitive domains under a consistent environment. We fine-tune models on ground truth data for intuitive physics and causal reasoning and find that this improves model performance in the respective fine-tuning domain. Furthermore, it can improve model alignment with human behavior. However, we find that task-specific fine-tuning does not contribute to robust human-like generalization to data with other visual characteristics or to tasks in other cognitive domains.

cs.LG↗

arXiv2025

Playing repeated games with Large Language Models

LLMs are increasingly used in applications where they interact with humans and other agents. We propose to use behavioural game theory to study LLM's cooperation and coordination behaviour. We let different LLMs play finitely repeated $2\times2$ games with each other, with human-like strategies, and actual human players. Our results show that LLMs perform particularly well at self-interested games like the iterated Prisoner's Dilemma family. However, they behave sub-optimally in games that require coordination, like the Battle of the Sexes. We verify that these behavioural signatures are stable across robustness checks. We additionally show how GPT-4's behaviour can be modulated by providing additional information about its opponent and by using a "social chain-of-thought" (SCoT) strategy. This also leads to better scores and more successful coordination when interacting with human players. These results enrich our understanding of LLM's social behaviour and pave the way for a behavioural game theory for machines.

cs.CL↗

arXiv2025

Centaur: a foundation model of human cognition

Establishing a unified theory of cognition has been a major goal of psychology. While there have been previous attempts to instantiate such theories by building computational models, we currently do not have one model that captures the human mind in its entirety. A first step in this direction is to create a model that can predict human behavior in a wide range of settings. Here we introduce Centaur, a computational model that can predict and simulate human behavior in any experiment expressible in natural language. We derived Centaur by finetuning a state-of-the-art language model on a novel, large-scale data set called Psych-101. Psych-101 reaches an unprecedented scale, covering trial-by-trial data from over 60,000 participants performing over 10,000,000 choices in 160 experiments. Centaur not only captures the behavior of held-out participants better than existing cognitive models, but also generalizes to new cover stories, structural task modifications, and entirely new domains. Furthermore, we find that the model's internal representations become more aligned with human neural activity after finetuning. Taken together, our results demonstrate that it is possible to discover computational models that capture human behavior across a wide range of domains. We believe that such models provide tremendous potential for guiding the development of cognitive theories and present a case study to demonstrate this.

cs.LG↗

arXiv2025

Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs

Paywalls, licenses and copyright rules often restrict the broad dissemination and reuse of scientific knowledge. We take the position that it is both legally and technically feasible to extract the scientific knowledge in scholarly texts. Current methods, like text embeddings, fail to reliably preserve factual content, and simple paraphrasing may not be legally sound. We propose a new idea for the community to adopt: convert scholarly documents into knowledge preserving, but style agnostic representations we term Knowledge Units using LLMs. These units use structured data capturing entities, attributes and relationships without stylistic content. We provide evidence that Knowledge Units (1) form a legally defensible framework for sharing knowledge from copyrighted research texts, based on legal analyses of German copyright law and U.S. Fair Use doctrine, and (2) preserve most (~95\%) factual knowledge from original text, measured by MCQ performance on facts from the original copyrighted text across four research domains. Freeing scientific knowledge from copyright promises transformative benefits for scientific research and education by allowing language models to reuse important facts from copyrighted text. To support this, we share open-source tools for converting research documents into Knowledge Units. Overall, our work posits the feasibility of democratizing access to scientific knowledge while respecting copyright.

cs.LG↗

arXiv2025

Are We Done with Object-Centric Learning?

Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various aims, including out-of-distribution (OOD) generalization, sample-efficient composition, and modeling of structured environments. Most research has focused on developing unsupervised mechanisms that separate objects into discrete slots in the representation space, evaluated using unsupervised object discovery. However, with recent sample-efficient segmentation models, we can separate objects in the pixel space and encode them independently. This achieves remarkable zero-shot performance on OOD object discovery benchmarks, is scalable to foundation models, and can handle a variable number of slots out-of-the-box. Hence, the goal of OCL methods to obtain object-centric representations has been largely achieved. Despite this progress, a key question remains: How does the ability to separate objects within a scene contribute to broader OCL objectives, such as OOD generalization? We address this by investigating the OOD generalization challenge caused by spurious background cues through the lens of OCL. We propose a novel, training-free probe called Object-Centric Classification with Applied Masks (OCCAM), demonstrating that segmentation-based encoding of individual objects significantly outperforms slot-based OCL methods. However, challenges in real-world applications remain. We provide the toolbox for the OCL community to use scalable object-centric representations, and focus on practical applications and fundamental questions, such as understanding object perception in human cognition. Our code is available here: https://github.com/AlexanderRubinstein/OCCAM.

cs.CV↗