论文检索

Deep Learning · Large Language Models

Yulin Chen, He He, Chen Zhao

Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language Model's (LLM) reasoning ability. However, the learning dynamics of RLVR remain underexplored. In this paper, we reveal a curious phenomenon: among hard examples that the model initially struggles with, a substantial subset remains unlearnable even when correct rollouts present. To understand the phenomenon, we first demonstrate that existing optimization and sampling techniques fail to resolve unlearnability. With cross-example gradient analysis, we show that unlearnable examples have fundamental representation issue, characterized by low gradient similarity with the rest of the examples and ungeneralizable reasoning patterns. We further show that representation flaws are difficult to mitigate in RL, as data augmentation does not improve gradient similarity. Our study provides the first systematic characterization of unlearnable data in RLVR training and reveals fundamental limitations in current RL approaches for reasoning tasks.

Applications · Time Series

Md Asif Bin Syed, Md Younus Ahamed, Azmine Toushik Wasi

Time series foundation models (TSFMs) have demonstrated strong performance on established benchmarks such as GIFT-Eval, Monash, and TSFM-Bench. However, these benchmarks pool datasets from many domains with uneven representation, which can obscure performance within specific application areas such as healthcare, finance, nature, retail, and transport. The necessity for domain-specific evaluation arises from the inherent structural diversity of time series data: clinical records often feature irregular sampling and informative missingness; financial sequences are characterized by high noise and stochastic trajectories; and environmental data, such as energy and weather, are governed by deterministic physical laws and strong seasonal hierarchies. Motivated by this heterogeneity, **we argue that TSFMs require explicit domain-specific benchmarks** so practitioners can reliably assess a model's utility within their own application area. This is because cross-domain differences in data generation, sampling irregularity, and nonstationarity under concept drift fundamentally shape forecasting difficulty and failure modes. As a result, strong performance on aggregated leaderboards may not translate to reliable deployment within a specific domain. To test this, we evaluated seven TSFMs across 72 datasets from six domains (healthcare, finance, energy, nature, transport, and retail) and found substantial cross-domain variability. These findings confirm that global benchmark scores can be misleading and that domain-aware evaluations are essential for trustworthy TSFM selection.

Deep Learning · Large Language Models

Shubham Parashar, Atharv Chagi, Jacob Helwig, Lakshmi Madhavarapu, Sushil Vemuri, James Caverlee, Dileep Kalathil, Shuiwang Ji

We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT performs well for autoregressive models, its use in DLMs faces challenges. Our observation and analysis reveal that vanilla SFT does not consider learnability, i.e., what and when tokens are learned. Specifically, we observe that rare tokens are difficult to learn when most of the input is masked. In contrast, it is straightforward and thus of little value to learn common tokens when most of the input is unmasked. To consider learnability, we propose LIFT, a learnability-informed fine-tuning strategy for DLMs. LIFT learns easy tokens when most of the input is noisy and hard tokens when more input is available, thereby aligning training with information available at different diffusion time steps. Our results show that LIFT outperforms existing SFT baselines across six reasoning benchmarks, achieving up to a 3x relative gain on AIME'24 and AIME'25.

Deep Learning · Generative Models and Autoencoders

Onkar Susladkar, Tushar Prakash, Gayatri Deshmukh, Kiet Nguyen, Jiaxun Zhang, Adheesh Juvekar, Tianshu Bao, Lin Chai, Sparsh Mittal, Inderjit Dhillon 等

We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific low-rank adapters, avoiding objective interference and representation entanglement, while a novel reference-based multimodal preference alignment optimizes relative outcomes under identical conditioning, improving faithfulness and controllability without large-scale retraining. UniDFlow achieves SOTA performance across eight benchmarks and exhibits strong zero-shot generalization to tasks including inpainting, in-context image generation, reference-based editing, and compositional generation, despite no explicit task-specific training.

Reinforcement Learning · Everything Else

Boyang Xu, Qing Zou, Siqin Yang, Hao Yan

Distributional RL models the full return distribution, but common categorical/quantile approaches rely on projection and independently sampled Bellman targets, which ignore the Bellman operator’s affine transport structure and yield high-variance learning signals. We introduce Path-Coupled Bellman Flows, a flow-matching framework that shares base noise to couple the generative trajectories of consecutive states, inducing a geometric Bellman scaling law between their velocity fields. This geometry motivates a $\lambda$-family of Bellman-flow objectives that functions as a control variate, reducing variance while retaining the same Bellman-consistent fixed point. Across toy diagnostics and offline RL benchmarks (OGBench, D4RL), our method improves training stability and achieves competitive or improved performance relative to prior distributional baselines.

Deep Learning · Algorithms

Yechan Kang, Yongjin Kweon, Mingyeong Seo, Sohee Park, Yeonguk jeon, Jongkil Park, Hyun Jae Jang, Jaewook Kim, Yeonjoo Jeong, Suyoun Lee 等

Training deep spiking neural networks (SNNs) remains challenging due to sharp loss landscapes and temporal inconsistency caused by surrogate gradients. To address these challenges, we propose a unified framework: adaptive and asymmetric surrogate gradients (A$^2$SG). The adaptive gradients adjust an effective window for spatio-temporal adaptation, reducing spatial gradient variation and maintaining directional consistency of gradients over time. The asymmetric gradients reflect neuronal dynamics by assigning larger gradients to neurons with higher membrane potentials, and we prove that they yield lower variation than symmetric surrogates. Our analysis further establishes a direct connection between local gradient variation and the curvature of the loss landscape, providing a principled explanation for how A$^2$SG promotes convergence to flatter minima and improves generalization. We conduct extensive experiments on diverse models, including CNN-based and Transformer-based SNNs, across various tasks such as image classification using both static and neuromorphic datasets, as well as segmentation. The results demonstrate that A$^2$SG consistently improves accuracy and energy efficiency, establishing it as a general and reliable solution for training deep SNNs.

Deep Learning · Large Language Models

Elron Bandel, Asaf Yehudai, Alexandre Lacoste, Avijit Ghosh, Graham Neubig, Margaret Mitchell, Michal Shmueli-Scheuer, Leshem Choshen

We call for the development of agentic systems that thrive in new environments. Agentic systems, comprising foundation models, tools, and an execution strategy, have demonstrated strong capabilities, yet their development is often constrained by narrow benchmarks and their operation is siloed to limited environments. This paper advocates for developing general, adaptive agents that excel across diverse environments, from terminals and web interfaces to biological and embodied settings. We examine current limitations, explain the potential of increased generality, and identify immediate development priorities. Finally, we argue that protocols and evaluation must prioritize adaptiveness to foster a shared ecosystem for general-purpose agentic systems.

Social Aspects · Fairness

Devon Jarvis, Richard Klein, Benjamin Rosman, Steven James, Stefano Sarao Mannelli

Model collapse, the degradation in performance that arises when generative models are trained on the outputs of prior models, is an increasing concern as artificially generated content proliferates. Related critiques of large language models have highlighted their tendency to reproduce frequent patterns in training data, their reliance on vast datasets, and their substantial environmental cost. Together, these factors contribute to data degradation, the reinforcement of cultural biases, and inefficient resource use. In this position paper we aim to combine these views and argue that model collapse threatens current efforts to democratise AI. By reducing training efficiency and skewing data distributions away from the tails of their support, model collapse disproportionately impacts low-resource and marginalized communities. We examine both the environmental and cultural implications of this phenomenon, situate our position within recent position papers on model collapse, and conclude with a call to action. Finally, we outline initial directions for mitigating these effects.

Social Aspects · Alignment

Jianwei Li, Jung-Eun Kim

This position paper argues that the AI/ML community should stop overclaiming and retire the label “positive backdoor”, and instead treat trigger-activated hidden behaviors as **Secret Alignment**. Crucially, protective claims based on Secret Alignment should be presumed *not secure by default* unless supported by rigorous, standardized evaluation. The Private AI era, enabled by open-weight LLMs and accessible training/inference stacks, turns language models into privately owned digital assets, creating security concerns around unauthorized access, model theft, and behavioral misuse. Recently, a line of work framed as “positive backdoors” has been proposed to address these challenges. To ground our position in evidence, we unify these proposals as covert trigger--behavior associations for access gating, ownership attribution, and safety enforcement, and evaluate three representative applications across six core properties: effectiveness, harmlessness, persistence, efficiency, robustness, and reliability. Our results reveal substantial brittleness---especially in the confidentiality, integrity, and availability (CIA)---of trigger--behavior mappings often underrepresented by existing claims. We further relate these outcomes to **behavior density** and **decision complexity**, offering a behavioral lens for understanding deployment-time risks and motivating community-wide evaluation that makes Secret Alignment claims provable.

Deep Learning · Large Language Models

Richardeau Gurvan, Gohar Dashyan, Erwan Le Merrer, Gilles Tredan

Literature reveals that a Large Language Model's (LLM) behavior is not only conditioned by its original weights but also its instance-level parameters, such as instructional prompt, sampling configuration or quantization. A model that generates safe outputs under one configuration may produce toxic content under another. However, current LLM identification techniques (such as fingerprinting) focus on intellectual property protection, and their design favors robustness to changes in these instance-level parameters. This poses a critical challenge for AI regulation in which compliance assessments target actual deployed behaviors, not model provenance. In this paper, we introduce instance-level fingerprinting, a regulator-oriented paradigm that distinguishes configurations of the same LLM. Our method (FLIPS) achieves 90\% identification accuracy across 205 model instances by exploiting biases in binary random generated sequences, compared to 35\% for the adapted baseline LLMmap. Our results demonstrate that instance-level fingerprinting is not only necessary for regulation, but also practically feasible.

Deep Learning · Large Language Models

Albert F. Modenbach

GPT-style language models are sensitive to single-token changes at generation points where the predicted probability distribution is spread across multiple tokens. Viewing this sensitivity as a geometric property, we derive an $\mathfrak{so}(n)$-valued 1-form that depends only on the geometry of the token embeddings. Despite this purely geometric origin, we show that its curvature is semantically meaningful: on chess reasoning tasks, the curvature couples to the world model of an off-the-shelf instruction-tuned model, with transformations clustering by board region and respecting piece importance. Our findings suggest that token space geometry directly reflects how models internally represent problems.

Applications · Time Series

Vasilii Feofanov, Songkang Wen, Shifeng Xie, Simon Roschmann, Marius Alonso, Hongbo Guo, Romain Ilbert, Malik TIOMOKO, Quentin Bouniot, Zeynep Akata 等

While foundation models have revolutionized various domains, their application to time series classification remains rather under-explored, with existing literature predominantly focused on forecasting. To bridge this gap, we introduce \textbf{Mantis}, a transformer-based foundation model pre-trained exclusively on synthetic data via self-supervised contrastive learning. We demonstrate that effective tokenization is critical to unlocking the full potential of transformers, proposing a novel token generator unit. Furthermore, we introduce an enhanced test-time methodology that bridges the performance gap between Mantis and strong specialized approaches by leveraging intermediate-layer representations, self-ensembling, and cross-model embedding fusion. Extensive experiments demonstrate that Mantis establishes a new state-of-the-art, outperforming existing foundation models across four diverse dataset collections covering various application domains.

Deep Learning · Large Language Models

Yizhou Liu, Sara Kangaslahti, Ziming Liu, Jeff Gore

Neural scaling laws relate loss to model size in large language models (LLMs), yet depth and width may contribute to performance differently, requiring more detailed studies. Here, we quantify how depth affects loss via analysis of LLMs and toy residual networks. We find loss scales inversely proportional to depth in LLMs, probably due to functionally similar layers reducing error through ensemble averaging rather than compositional learning or discretizing smooth dynamics. This regime is inefficient yet robust and may arise from the architectural bias of residual networks and target functions incompatible with smooth dynamics. Our findings suggest that improving LLM efficiency may require architectural innovations to encourage compositional use of depth.

Applications · Computer Vision

Shayda Moezzi, Umer Saleem, Andong Deng, Chen Chen, Sarah Ostadabbas

The essence of video lies in pixel dynamics: motion, state transitions, and the flow of visual information across frames. Video Large Language Models (LLMs) have rapidly become the dominant paradigm for video understanding in computer vision, sophisticated multimodal reasoning over complex, long-form visual streams. In this position paper, we argue that recent progress in video understanding is measured by benchmarks and protocols that can be solved without reliably perceiving spatiotemporal evidence, rewarding language-driven plausibility over video-grounded inference. We identify two coupled failure modes that consistently emerge across recent Video LLM evaluations: (i) static-cue dominance, where appearance and context outweigh spatiotemporal evidence, and (ii) prior-driven temporal hallucination, where learned regularities fill in temporal and causal structure when dynamics are subtle or counterintuitive. We synthesize recent diagnostic probes that expose these failure modes into a call to action for the community: to re-center video understanding on what a video uniquely contains, namely, dynamic evidence that unfolds over time, by enforcing spatiotemporal grounding in both models and benchmarks, before the pixel dynamics are lost in plain sight.

Social Aspects · Alignment

Vijay Keswani, Breanna Nguyen, Cyrus Cousins, Vincent Conitzer, Walter Sinnott-Armstrong, Jana Schaich Borg

AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settings, particularly high-stakes decision-making, we need accurate cognitively-aligned AI systems that reason similarly to their users, and faithfully communicate their reasoning. We review evidence that cognitive alignment improves understandability and trustworthiness, and provide new survey data showing that many users find cognitive alignment “essential” when an AI’s rationale for a judgment or action is important to them. We outline the gaps between existing alignment methods and what is needed to achieve cognitive alignment, and present a research agenda to address these gaps. We argue that cognitive alignment represents a likely impediment to AI adoption in many envisioned applications, and that addressing it is important for creating AI systems on which users are both willing and justified to rely.

Deep Learning · Generative Models and Autoencoders

Peter Holderrieth, Douglas Chen, Luca Eyring, Ishin Shah, Giri Anantharaman, Yutong He, Zeynep Akata, Tommi Jaakkola, Nicholas Boffi, Max Simchowitz

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient reward alignment should be a property of the generative model itself, not an afterthought, and redesign the model for adaptability. We propose Diamond Maps, a stochastic flow-map model that enables efficient and accurate alignment to arbitrary rewards at inference time. Diamond Maps amortize many simulation steps into a single-step sampler, like flow maps, while preserving the stochasticity required for optimal reward adaptation. This design makes search, Sequential Monte Carlo, and guidance scalable by enabling efficient and consistent estimation of the value function. Our experiments show that Diamond Maps can be learned efficiently via distillation from GLASS Flows, achieve stronger reward-alignment performance, and scale better than existing alignment methods. Overall, our results point toward a practical route to generative models that can be rapidly adapted to arbitrary preferences and constraints at inference time.

Deep Learning · Large Language Models

Chengcheng Wang, Jianyuan Guo, Hongguang Li, Yuchuan Tian, Ying Nie, Chang Xu, Kai Han

Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and image position indices and can introduce spurious cross-modal relative-position bias. We propose Per-Token Distance (PTD) to quantify cross-modal positional disentanglement, and we prove that $\mathrm{PTD}=0$ is a sufficient condition to eliminate the geometric attention bias induced by RoPE. Guided by this criterion, we introduce Circle-RoPE, which remaps 2D image-token coordinates onto an annulus orthogonal to the text position axis, yielding a cone-like geometry where each text token is equidistant to all image tokens while preserving intra-image spatial structure. We further propose Alternating Geometry Encoding (AGE) to improve robustness by alternating RoPE variants across layers, and experiments on diverse VLM backbones and multimodal benchmarks show consistent gains in spatial grounding and visual reasoning.

Applications · Chemistry, Physics, and Earth Sciences

Matteo Raviola, Benjamin Peherstorfer

Dirac-Frenkel instantaneous residual minimization evolves nonlinear parametrizations of PDE solutions in time, but ill-conditioning can render the parameter dynamics non-unique. We interpret this non-uniqueness as a gauge freedom: nullspace directions that leave the time derivative unchanged can be used to select better-conditioned parameter velocities. Building on Onsager's minimum-dissipation principle, we introduce a history variable---interpretable as momentum---and inject it only along the nullspace directions. The resulting Dirac-Frenkel-Onsager dynamics preserve instantaneous residual minimization, in contrast to standard regularization that can introduce bias, while promoting temporally smooth parameter evolution. Examples demonstrate that the approach leads to increased robustness in singular and near-singular regimes.

General Machine Learning · Evaluation

Christian Marius Lillelund, Shi-ang Qi, Russell Greiner, Christian Fischer Pedersen

The current state of evaluation in survival analysis is plagued by the persistent use of evaluation metrics in ways that are misaligned with the stated modeling objective. In addition, many such evaluations are based on censoring assumptions that are left implicit or unjustified. This means that the reported performance can be misleading and may fail to answer the scientific or modeling question the evaluation was intended to address. In this position paper, we present a critical analysis of evaluation practices in survival analysis and highlight why evaluation in survival analysis fundamentally differs from standard regression or classification due to censoring. We place particular focus on concordance-based measures, such as the C-index, which our findings indicate are heavily overused in the literature. To help identify appropriate metrics, we propose a set of key desiderata and introduce a double-helix ladder, in which valid evaluation requires alignment between metric and modeling assumptions, and we provide empirical evidence that this is effective. We conclude by providing practical guidance on how to evaluate a survival model.

Deep Learning · Sequential Models, Time series

Md Mahmuddun Nabi Murad, Yasin Yilmaz

Early and accurate detection of anomalies in time-series data is critical due to the substantial risks associated with false or missed detections. While MLP-based mixer models have shown promise in time-series analysis, they do not maintain temporal causality during data processing. Moreover, real-world multivariate time series often contain numerous channels with diverse inter-channel correlations. Spurious correlations in the reconstructed time series lead to noisy representations, resulting in inaccurate anomaly detection. In addition, anomaly scoring methods that ignore temporal continuity can mislead sequential detection. To address these challenges, we propose a cluster-aware causal mixer for multivariate time-series anomaly detection. Channels are grouped into clusters based on their correlations, and each cluster is embedded through a dedicated embedding layer. A causal mixer is introduced to integrate information while maintaining temporal causality. We further develop a sequential anomaly-scoring method that accumulates evidence over time and refines anomaly boundaries. Our proposed model operates in an online fashion, making it suitable for real-time time-series anomaly detection. Experimental evaluations across six public benchmark datasets demonstrate that the proposed approach consistently achieves superior performance.