arXiv:2603.22167v1 Announce Type: cross Abstract: We study calibeating, the problem of post-processing external forecasts online to minimize cumulative losses and match an informativeness-based benchmark. Unlike prior work, which analyzed calibeating for specific losses with specific arguments, we reduce calibeating to existing online learning techniques and obtain results for general proper losses. More concretely, we first […]
A Stable Neural Statistical Dependence Estimator for Autoencoder Feature Analysis
arXiv:2603.11428v2 Announce Type: replace-cross Abstract: Statistical dependence measures like mutual information is ideal for analyzing autoencoders, but it can be ill-posed for deterministic, static, noise-free networks. We adopt the variational (Gaussian) formulation that makes dependence among inputs, latents, and reconstructions measurable, and we propose a stable neural dependence estimator based on an orthonormal density-ratio decomposition. […]
Examining the impact of forcing function inputs on structural identifiability
arXiv:2407.02771v2 Announce Type: replace Abstract: For mathematical and experimental ease, models with time varying parameters are often simplified to assume constant parameters. However, this simplification can potentially lead to identifiability issues (lack of uniqueness of parameter estimates). Methods have been developed to algebraically and numerically determine the identifiability of a model, as well as resolve […]
A Training-free Method for LLM Text Attribution
arXiv:2501.02406v5 Announce Type: replace-cross Abstract: Verifying the provenance of content is crucial to the functioning of many organizations, e.g., educational institutions, social media platforms, and firms. This problem is becoming increasingly challenging as text generated by Large Language Models (LLMs) becomes almost indistinguishable from human-generated content. In addition, many institutions use in-house LLMs and want […]
TRI-DEP: A Trimodal Comparative Study for Depression Detection Using Speech, Text, and EEG
arXiv:2510.14922v2 Announce Type: replace Abstract: Depression is a widespread mental health disorder, yet its automatic detection remains challenging. Prior work has explored unimodal and multimodal approaches, with multimodal systems showing promise by leveraging complementary signals. However, existing studies are limited in scope, lack systematic comparisons of features, and suffer from inconsistent evaluation protocols. We address […]
Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
arXiv:2507.13340v4 Announce Type: replace-cross Abstract: The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action spaces make them difficult to leverage. Our main insight is that skills performed across different embodiments produce […]
EvoOpt-LLM: Evolving industrial optimization models with large language models
arXiv:2602.01082v2 Announce Type: replace Abstract: Optimization modeling via mixed-integer linear programming (MILP) is fundamental to industrial planning and scheduling, yet translating natural-language requirements into solver-executable models and maintaining them under evolving business rules remains highly expertise-intensive. While large language models (LLMs) offer promising avenues for automation, existing methods often suffer from low data efficiency, limited […]
End-to-End Training for Unified Tokenization and Latent Denoising
arXiv:2603.22283v1 Announce Type: cross Abstract: Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be trained in the frozen latent space. We propose UNITE – an autoencoder architecture for unified tokenization and latent […]
FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse and Prover-Effective Autoformalization
arXiv:2603.19828v2 Announce Type: replace Abstract: Autoformalization aims to translate natural-language mathematics into compilable, machine-checkable statements. However, semantic consistency does not imply prover effectiveness: even semantically consistent formalizations can differ substantially in proof-search cost and success rate. In this work, we formulate autoformalization as a budgeted, test-time search for semantically consistent repertoires, and propose FormalEvolve, a […]
Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
arXiv:2601.10679v2 Announce Type: replace Abstract: Hierarchical reasoning model (HRM) achieves extraordinary performance on various reasoning tasks, significantly outperforming large language model-based reasoners. To understand the strengths and potential failure modes of HRM, we conduct a mechanistic study on its reasoning patterns and find three surprising facts: (a) Failure of extremely simple puzzles, e.g., HRM can […]
DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition
arXiv:2502.00618v3 Announce Type: replace-cross Abstract: Continual learning of vision-language models (VLMs) focuses on leveraging cross-modal pretrained knowledge to incrementally adapt to expanding downstream tasks and datasets, while tackling the challenge of knowledge forgetting. Existing research often focuses on connecting visual features with specific class text in downstream tasks, overlooking the latent relationships between general and […]
AgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents
arXiv:2603.21613v1 Announce Type: cross Abstract: Recommender agents built on Large Language Models offer a promising paradigm for recommendation. However, existing recommender agents typically suffer from a disconnect between intermediate reasoning and final ranking feedback, and are unable to capture fine-grained preferences. To address this, we present AgenticRec, a ranking-oriented agentic recommendation framework that optimizes the […]