Uncertainty estimation has been a long-standing challenge in AI models; it amounts to "knowing what you don't know," and metacognition is notoriously difficult even for humans (cf. the Dunning-Kruger effect). Although it is still far from solved even in simpler classification systems, tackling it in multimodal large language models (MLLMs) is becoming increasingly important. Within MLLMs, uncertainty can stem from any of the diverse sources as well as from their relationships, and further can stem from the unbounded answers in the open-ended setting. To tackle the issues, we propose CoMet, an MLLM uncertainty estimation method by decomposing uncertainty into a context-specific term and a multiplicity-specific term. The former captures ambiguity induced by the given context (e.g., task or prompt), while the latter captures how many plausible answers determined by the context remain compatible with the given input. We train a lightweight post-hoc uncertainty module to estimate these quantities, which enables efficient uncertainty estimation without autoregressive answer generation or repeated sampling. Experiments on various open-ended multimodal benchmarks, hallucination detection, and multiple-choice visual question answering benchmarks show that CoMet consistently improves uncertainty estimation over existing baselines while remaining efficient in practice. Code is available at https://github.com/princetonvisualai/comet_uncertainty
The most widely used RANSAC variants score a candidate model by summing per-point scores that fall to zero beyond a threshold. These scores derive from the negative log-likelihood of a Gaussian-uniform mixture. The threshold separates inliers, which follow the noise model, from outliers, and it is a function of the observation noise level, also known as the inlier scale. We remove this dependence on the threshold by reversing the usual order of RANSAC inference: rather than estimating the scale and then scoring against it, we marginalize the scale in closed form for a fixed inlier partition and then optimize over partitions. The resulting score is maximized by a single sort followed by a linear sweep. A single closed-form expression spans informative and non-informative priors, so the same score adapts to datasets with extensive or limited ground-truth annotation. The proposed score has a single hyperparameter, the half-width of the uniform outlier distribution. We show that this half-width is far less sensitive to miscalibration than the inlier threshold and is easier to cross-validate. The proposed score is the first likelihood-based RANSAC score in which the inlier scale is absent from the formula. Project page: https://ransacscoringdoneright.github.io
Does intelligence require the ability to reason about phenomena beyond direct experience? It is natural to suspect that some complex thought cannot be captured through language alone. However, of particular concern to this work, is whether visualising counterfactual events can complement language as a mechanism for complex thought. We ask whether LLMs can be trained to utilise such visualisation mechanisms, in a way that benefits their reasoning abilities. Motivated by this question, we propose Einstein World Models. EWMs are a blueprint for LLM-based reasoning systems that place visual-temporal rollouts inside the reasoning trace, allowing them to reason in ways that text alone may not support well. In an EWM, the LLM calls a world-module (not to be confused with a world model), to produce short rollouts of scenes under consideration. The returned rollout is treated not as the answer, but as an inspectable hypothesis that can support later reasoning. Einstein World Models extend the capability of LLMs for tool calling (such as web search or code execution), into the domain of visual thought experiments.
While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requires architectures that balance efficient training with highly expressive latent states. Echo State Networks (ESNs) offer a compelling approach by utilizing fixed recurrent weights to circumvent backpropagation through time, enabling a closed-form training solution. However, achieving the expressivity needed for complex tasks demands large reservoirs, exposing an $\mathcal{O}(N^2)$ state-update bottleneck that prevents ESNs from matching the scale of contemporary recurrent models. To address this limitation, we introduce Frequency Domain Reservoir Computing (FRESCO), an ESN architecture operating entirely in the frequency domain while avoiding domain-shift overheads to achieve $\mathcal{O}(N)$ complexity for dense, non-linear updates via structured circulant recurrence. By employing a novel dimensional zero-padding input embedding, a packed frequency-domain readout, and a natively applied frequency-domain non-linearity, FRESCO drastically reduces computational costs and energy consumption of training and inference. Furthermore, FRESCO achieves competitive predictive performance on memory benchmarks, sequential classification, and multivariate long-horizon forecasting, offering a scalable and energy-efficient path forward for dense recurrent architectures.
Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their success reflects genuine causal understanding or sophisticated pattern matching over visual-textual correlations. Inspired by Russell's inductivist turkey, we introduce Counterfactual-World (CF-World), a counterfactual benchmark designed to investigate whether text-to-image models can generate images under rules that systematically contradict real-world priors. CF-World organizes each scenario into three progressive levels: factual generation under ordinary world knowledge, explicit counterfactual generation with direct visual instructions, and implicit counterfactual generation requiring causal deduction from altered rules. We evaluate open-source and closed-source text-to-image models using CF-Eval, a scoring pipeline based on vision-language models. We report the scores at each prompt level as the primary results and use Prior Resistance Rate (PRR) and Reasoning Retention Rate (RRR) as auxiliary descriptive indicators. All evaluated models score lower on counterfactual prompts than on factual prompts. Diagnostic experiments reveal difficulties in following altered rules and recombining rarely co-occurring visual attributes. The gains from rephrasing object and attribute names are consistent with a role for learned visual priors in counterfactual generation. Our benchmark and evaluation code are publicly available at https://jylei16.github.io/CF-World.github.io/.
We present MorfFlex, a morphological dictionary architecture suitable for languages with extensive regularity in both inflection and derivation. As the primary example of MorfFlex in use we introduce MorfFlex CZ, a morphological dictionary of Czech. It is distributed as a simple, unstructured list of <wordform, lemma, tag> triplets, however, its manually maintained, unpublished source files and conversion scripts encode a sophisticated system of inflectional and derivational patterns. These patterns dramatically reduce the otherwise enormous size of the dictionary, which currently contains over 100 million wordforms and more than 1 million lemmas. The MorfFlex CZ dictionary serves as an essential resource for ensuring the consistency of manual morphological annotation in the Prague Dependency Treebanks and underpins state-of-the-art automatic tools such as MorphoDiTa. In this paper, we focus on: (i) presenting an effective method for managing the rich morphological system within the dictionary, and (ii) demonstrating the utility of such a language resource for maintaining annotation consistency in corpora and supporting the development of advanced NLP applications.
Czech has been part of Universal Dependencies since its first release in 2015. It has also been one of the best represented languages, with the Prague Dependency Treebank being order of magnitude larger than most other UD treebanks. More recently, three other datasets from the Prague family were added and the annotations thoroughly revisited, forming the "Prague Dependency Treebank-Consolidated" (PDT-C). In comparison to the original PDT, PDT-C is more than twice as large, but it is also much more diverse in terms of genres and domains. In this paper, we describe the conversion of the new resource to Universal Dependencies. While the two annotation schemes are relatively similar at the first sight, there are numerous small differences in topology of the dependency structures and in granularity of the POS and relation type inventories. We demonstrate a selection of such differences on examples, discuss the diverging motivations, as well as ways to overcome the differences during conversion. We argue that while PDT is less "universal" and more tightly bound to one language, its multi-layer annotation is rich and provides all information needed for basic UD trees, and much more.
The Prague Dependency Treebank framework is unique in its attempt to systematically include and link different layers of language, including a meaning representation with several types of inter-sentential phenomena, especially coreference and discourse relations. We present its second consolidated version (PDT-C 2.0), which concludes almost 30-years long project of sustained development of the resource to a uniformly and coherently annotated, genre-diversified, almost 4 million token language resource of Czech language, with accompanying fully compatible lexicons. In addition to continuous linguistic research, the richly linguistically annotated corpus is also widely used in international comparisons of the development of traditional and novel NLP tools as well as in conversions into other formalisms. The corpus and the trained parsers are available under the CC BY-NC-SA licence.
Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's aligned character rather than direct learning of harmful content. Motivated by this connection, we study self-modeling interventions: specifically self-recognition and self-reports as character-targeted interventions that are distinct from existing in-training defenses. We conduct two-stage finetuning experiments across three models (GPT-4.1, Qwen2.5-32B-Instruct, Seed-OSS-36B-Instruct) and multiple EM datasets to compare self-recognition finetuning against benign finetuning baselines (correct domain-specific data, general knowledge, and word counting), finding it an effective defense in both reversal and prevention settings. For prevention, only self-recognition finetuning consistently reduces misalignment without exacerbating any individual metric, suggesting that character fortification specifically drives prevention. We also conduct in-training experiments across these models to compare the effectiveness of self-reports with benign interleaving and inoculation prompting. We provide further evidence for EM's relation to the LLM's default character by showing that EM finetuning leads to fragmentation of LLM's identity self-reports, reduces self-recognition performance to about chance, artificially corrupting self-recognition exacerbates misalignment caused by EM finetuning, and finetuning on self-reports from EM finetuned models can transfer misalignment. Together, these findings reframe EM not as the adoption of a coherent misaligned persona but as the destabilization of aligned character.
Location encoders transform geographic coordinates into high dimensional embeddings for downstream machine learning, but it is unclear how well these representations capture interpretable spatial effects. We benchmark whether GeoShapley, a game-theoretic explainer that treats all location features as a single joint player, can recover spatially varying coefficients from models built on location-encoder embeddings. Eleven encoders from the TorchSpatial framework are evaluated against a synthetic process with known coefficients, across three scales (grid, county, global), with and without raw coordinates alongside the embedding, and under untrained and contrastively trained conditions. Measuring recovery as the correlation between estimated and true coefficients, we report how it varies with scale and encoder architecture and compare the embeddings against a raw-coordinate baseline. Recovery of the primary coefficient is consistently high across encoders, whereas recovery of a secondary coefficient is more scale-dependent, differing most at the global scale; the raw-coordinate baseline remains competitive throughout.
Numerical methods and neural networks have transformed our understanding of nonlinear partial differential equations (PDEs), yet discovering mathematical representations that explain their dynamics remains largely an expert task. We introduce Agentic Symbolic Search (ASYS), in which coding agents construct and refine explicit approximations from a known PDE and supplied mathematical knowledge. ASYS couples evolutionary search over differentiable symbolic programs with gradient-based fitting, using the governing equation to evaluate candidates and guide their revision. For a singular generalized Constantin-Lax-Majda profile, ASYS infers a missing decay term that sets how fast the field approaches its singular-time limit, and builds a basis that fits the profile to a median error of $3.90\times10^{-5}\%$. For Fujita blow-up, separating diffusion from reaction and deriving a local response lowers the supplied formula's error from 55.5% to 0.0879%. For Allen-Cahn interfaces, a 14-parameter construction yields a mode-coupling law confirmed by independent simulations. These studies show how agentic search develops mathematical starting points into accurate, analyzable approximations.
Hallucinations remain a major obstacle to deploying large language models (LLMs) in knowledge-intensive settings, where generated responses must be faithfully grounded in provided evidence. Reinforcement learning (RL) is a promising direction for hallucination mitigation, but response-level faithfulness rewards suffer from a granularity mismatch: localized hallucinations can cause supported content to receive spurious penalties. Although recent work introduces fine-grained feedback such as claim-level verification and token-level rewards, unbalanced credit assignment can still induce length, verbosity, or optimization-noise biases. We propose BALTO, a Balanced Token-level Policy Optimization framework for hallucination mitigation. BALTO extracts checkable factual claims, verifies them against the reference context, and projects claim-level judgments to token-level labels. A balanced token-level credit assignment mechanism is introduced into the framework. This design redistributes probability mass from unsupported content toward faithful content, rather than suppressing the entire response. We systematically analyze the limitations of response-level rewards from a theoretical standpoint, and prove BALTO's advantages in training stability and optimization efficiency for hallucination mitigation. Experiments on ConFiQA, RAGTruth, and FinLLM-Eval show that BALTO achieves the highest faithfulness across all six model--benchmark settings and consistently outperforms existing post-training baselines in Q-Score, demonstrating a stronger faithfulness--informativeness trade-off. The code is released at https://github.com/NingLi670/BALTO.
Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically limited to text encoding, while denoising is handled by newly trained generative backbones. The emergence of representation autoencoders (RAEs) shifts the generation target toward semantically structured visual representations, creating a latent space that is more compatible with pretrained LLM priors. Inspired by multimodal LLMs (MLLMs), where an MLP projector is sufficient to align clean visual representations with a pretrained LLM, we repurpose the MLLM itself as a noisy representation encoder, extending this mechanism from clean to noisy inputs. We present RepFusion, which uses the resulting MLLM outputs as the conditioning signal for a diffusion transformer. In controlled comparisons at similar inference budgets, RepFusion outperforms baselines that devote comparable capacity to newly initialized denoisers. Reusing MLLM outputs across denoising steps further accelerates inference while retaining performance comparable to per-step MLLM recomputation. These results demonstrate that MLLMs provide strong priors for denoising visual representations.
Over the last decade, building human-level artificial general intelligence has moved from far-fetched speculation to being a concrete next-decade target for many of the largest AI organizations. Achieving this goal would have profound and far-reaching impacts on human society, which raises many complex questions for the decade ahead. This report investigates how AI itself might continue to develop in a post-AGI world along the continuum of machine intelligence. The endpoint of this continuum, Universal AI, is theoretically well understood, which provides some formal grounding for the main focus of this report: the transition from human-level AGI to artificial general superintelligence, which can intuitively be understood as a system that is more intelligent and cognitively capable than large organizations of humans. After characterizing ASI, the report discusses four potential pathways from AGI to ASI: scaling AGI, AI paradigm shifts, ASI emerging from large-scale multi-agent collectives, and recursive improvement. The report then discusses possible frictions and bottlenecks along these pathways. Determining whether the impact of these frictions will be negligible or substantial raises a number of concrete open research questions. While large uncertainties for predicting ASI progress remain, it cannot be ruled out that AI progress might continue to accelerate over the next years. This would imply that the image of a single transformative step change, caused by the introduction of human-level AGI into our society, could be inaccurate. More apt might be the prospect of a series of transformative societal changes caused by AI-enabled progress and breakthroughs across many areas of science and technology. Preparing for this prospect requires a massively interdisciplinary endeavor of global scope and interest.
Reflectance confocal microscopy (RCM) provides noninvasive, cellular-resolution "optical biopsies" of human skin in vivo by acquiring en-face images at successive depths, forming a sparse z-stack. Due to optical limitations, these stacks are anisotropic 3D volumes with lateral resolution (0.5 $\mu$m) $\sim$6 times higher compared to axial resolution, which is defined by the optical sectioning (3 $\mu$m), limiting the interpretation of tissue. Our goal is to provide continuous-depth visualization by interpolating intermediate sections and making the 3D volume isotropic. Such a representation permits arbitrary-direction sectioning, including histopathology-like cross-sectional examination, without requiring per-patient optimization. To that end, we introduce the first RCM-specific novel-view synthesis (NVS) approach, CD-RCM, a feedforward model that predicts realistic, unseen depths from sparsely sampled RCM stacks. Classical neural rendering methods focus on reconstruction from surface-level multi-view observations. In contrast to surface-level camera views, RCM can acquire optically sectioned en-face images of tissue beyond the surface up to 200 $\mu$m. However, during visualization of the RCM stacks, observations of the shallower sections (towards the surface) obscure the deeper ones. This unique axial imaging geometry and layer-dependent anatomical organization motivated our development of a tailored architectural and training framework that explicitly accounts for RCM's depth-resolved, occlusive imaging physics. Experiments demonstrate that CD-RCM achieves high-fidelity novel-view synthesis with sub-second inference time.
Unsupervised video object-centric learning aims to decompose dynamic scenes into persistent, object-level representations without supervision. However, existing slot-based methods struggle to maintain stable object identity in challenging settings such as rapid motion and partial occlusion. First, they typically encode both the per-frame appearance of an object and its identity across frames in a single slot vector, creating an objective conflict that leads to slot swapping: reconstruction requires sensitivity to transient visual changes, whereas temporal consistency requires invariance to them. Second, the token renormalization used in Slot Attention can amplify weakly attending slots, allowing them to absorb tokens from other objects and destabilize slot-to-object correspondence. We propose Dual-State Slot Attention (DSSA), a fully self-supervised framework that addresses these limitations by separating appearance from identity and by reducing spurious updates from weakly matching slots. DSSA decomposes each slot into a local state for per-frame appearance and an identity state for temporally stable object information, thereby aligning reconstruction and temporal consistency with separate representations. The identity state is updated through a learned recurrent transition that acts as a temporal filter on the local state, while competition-modulated aggregation (CMA) down-weights updates from weakly matching slots and prevents them from absorbing tokens from other objects. Experiments on MOVi-C, MOVi-D, and YouTube-VIS demonstrate that DSSA consistently improves segmentation quality and temporal consistency over prior methods, while also yielding stronger downstream object recognition and video dynamics prediction. Code is available at https://uark-aicv.github.io/dssa/.
Research on bias in large language models (LLMs) has predominantly focused on third-person audits, which study how models represent or evaluate demographic groups as external subjects. However, this paradigm overlooks a structural blind spot because the user is absent from the audit. In practice, LLMs are used in open-ended, personal interactions, during which the model implicitly represents the user and adjusts its responses accordingly. When identical requests yield different responses depending on who is asking, bias manifests not in how the model describes others but in how it treats its interlocutor. Empirical first-person bias studies are multiplying, but they use different cues, outcomes, and validation choices, which makes their results hard to compare. We propose Situated Interaction Auditing (SIA), a shared diagnostic framework for this literature. It introduces a typology of user profile signals---names and surface markers, writing style and dialect, and stated identity---together with design principles and outcome measures that let studies be compared and accumulated. We instantiate the framework in a case study of Chilean first and last names across nine task domains and three models, and we close with guidance for practitioners and open questions for researchers.
Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions. Yet, their ability to do so in high-stakes domains such as health remains unclear. We introduce SciConBench, a large-scale live benchmark of 9.21K questions and expert-written conclusions from systematic reviews to evaluate open-domain scientific conclusion synthesis in health and medical domains. The benchmark draws on an expert-validated automated evaluation pipeline that decomposes conclusions into atomic facts and measures correctness and comprehensiveness via factual precision and recall. To mitigate data leakage, we further introduce SciConHarness, a clean-room evaluation harness that equips agents with controlled web interaction to ensure valid measurement. Evaluating 8 frontier models and deep research agents, we find that factual quality remains low: under clean-room settings, the best agent achieves only a factual F1 of 0.337. Our clean-room setting consistently reduces performance relative to unconstrained evaluation, suggesting that leakage inflates estimates of models' true synthesis capabilities. Finally, we audit consumer-facing agents (e.g., Google AI Overview, OpenEvidence) and find they frequently generate incomplete and sometimes contradictory conclusions, even when the ground-truth answer is available. Overall, our results show that reliable synthesis of scientific conclusions in health remains an open challenge, and that clean-room evaluation is essential for assessing open-domain AI agents.
When a model behaves in unexpected ways, we want to know why, but its intent cannot be observed directly, and its self-reports may be rationalizations. We introduce comparative motivation profiles, which treat intent as propensity: we edit the model's beliefs about facts that a hypothesized motivation would depend on and measure how its behavior changes. To keep artifacts of the editing method from driving the result, we edit two minimally different hypotheses in the same way, with matched amplify and suppress edits; we call this symmetric belief editing. We apply it to alignment faking in four open-weight model organisms, contrasting scheming, which tracks the training consequences of compliance, with performative misalignment, which tracks what researchers expect to observe, and edit beliefs with synthetic document fine-tuning (SDF), activation steering, and prompting. Under SDF, amplifying performative beliefs raises alignment faking on every model, while scheming edits move it less or shift compliance in the monitored and unmonitored conditions alike. Steering on model organisms changes compliance along the expectation-tracking direction but mainly the reasoning along the consequence-tracking direction, and prompting agrees. In these organisms, alignment faking follows what the models infer their evaluators expect, which puts it closer to sycophancy than to deceptive alignment.
Surveys of hallucination classify errors by how an output relates to its source, and often explain them by the model's structure: attention retrieves by association, the maximum-likelihood objective has no term for truth, and left-to-right decoding commits to early tokens. Data, on this account, makes these failures worse rather than causing them. The account is usually argued rather than tested. We test it with interventions that need only sampling access. Study 1 holds pretraining data, tokenizer and scale fixed and swaps attention for a state-space mixer, using five Pythia/Mamba pairs from 130M to 2.8B parameters and four further attention models, on 111 facts presented with a planted false or a planted true statement. Swapping the mixer leaves free-recall failure unchanged (both 2.8B models answer 3 of 200 SimpleQA questions), but it changes what happens to a defect in the input. From 410M upwards, every attention model repeats the planted falsehood more often than its matched state-space model (2.8B: 650 vs. 566 of 666 items, p = 2.5e-20), also on facts both models know, while the state-space models can still read planted facts they did not know. Study 2 replaces the first wrong fact in 111 erroneous answers from three instruction-tuned models. The correct fact cuts the share of answers with a downstream error from 92.5% to 48.1%, but a different wrong fact works as well (p = 0.38), and the models give the right answer in isolation on only 2 of 111 items. The structural account survives in a narrower form. The mixing component decides whether a defect in the context becomes an output error, commitment decides how an error spreads, and on long-tail questions the first error comes from missing knowledge, not from a suppressed truth.