Regret Matching+ (RM+) variants are widely used to build superhuman Poker AIs, yet few studies investigate their last-iterate convergence in learning a Nash equilibrium (NE). Although their last-iterate convergence is established for games satisfying the Minty Variational Inequality (MVI), no studies have demonstrated that these algorithms achieve such convergence in the broader class of games satisfying the weak MVI. A key challenge in proving last-iterate convergence for RM+ variants in games satisfying the weak MVI is that even if the game's loss gradient satisfies the weak MVI, RM+ variants operate on a transformed loss feedback which does not satisfy the weak MVI. To provide last-iterate convergence for RM+ variants, we introduce a concise yet novel proof paradigm that involves: (i) transforming an RM+ variant into an Online Mirror Descent (OMD) instance that updates within the original strategy space of the game to recover the weak MVI, and (ii) showing last-iterate convergence by proving the distance between accumulated regrets converges to zero via the recovered weak MVI of the feedback. Inspired by our proof paradigm, we propose Smooth Optimistic Gradient Based RM+ (SOGRM+) and show that it achieves last-iterate and finite-time best-iterate convergence in learning an NE of games satisfying the weak MVI, the weakest condition among all known RM+ variants. Experiments show that SOGRM+ significantly outperforms other algorithms. Our code is available at https://github.

The rise of parallel computing hardware has made it increasingly important to understand which nonlinear state space models can be efficiently parallelized.

We propose Fast Long-context Adaptive Memory for Event (FLAME), a novel scalable architecture that combines neuro-inspired feature extraction with robust structured sequence modeling to efficiently process asynchronous and sparse event camera data. As a departure from conventional input encoding methods, FLAME presents Event Attention Layer, a novel feature extractor that leverages neuromorphic dynamics (Leaky Integrate-and-Fire (LIF)) to directly capture multi-timescale features from event streams. The feature extractor integrates with a structured state-space model with a novel Event-Aware HiPPO (EA-HiPPO) mechanism that dynamically adapts memory retention based on inter-event intervals to understand relationship across varying temporal scales and event sequences. ANormal Plus Low Rank (NPLR) decomposition reduces the computational complexity of state update from O(N2) to O(Nr), where N represents the dimension of the core state vector and r is the rank of a low-rank component (with r N). FLAME demonstrates state-of-the-art accuracy for event-by-event processing on complex event camera datasets.

The rise of Large Language Models (LLMs) has driven progress in reasoning tasks, from program synthesis to scientific hypothesis generation, yet their ability to handle ranked preferences and structured algorithms in combinatorial domains remains underexplored. We study matching markets, a core framework behind applications like resource allocation and ride-sharing, which require reconciling individual ranked preferences to ensure stable outcomes. We evaluate seven stateof-the-art models on a hierarchy of preference-based reasoning tasks--ranging from stable-matching generation to instability detection, instability resolution, and finegrained preference queries--to systematically expose their logical and algorithmic limitations in handling ranked inputs. Surprisingly, even top-performing models with advanced reasoning struggle to resolve instability in large markets, often failing to identify blocking pairs or execute algorithms iteratively. We further show that parameter-efficient fine-tuning (LoRA) significantly improves performance in small markets, but fails to bring about a similar improvement in large instances, suggesting the need for more sophisticated strategies to improve LLMs' reasoning with larger-context inputs.

Preference-based data often appear complex and noisy but may conceal underlying homogeneous structures. This paper introduces a novel framework of ranking structure recognition for preference-based data. We first develop an approach to identify dynamic ranking groups by incorporating temporal penalties into a spectral estimation for the celebrated Bradley-Terry model. To detect structural changes, we introduce an innovative objective function and present a practicable algorithm based on dynamic programming. Theoretically, we establish the consistency of ranking group recognition by exploiting properties of a random'design matrix' induced by a reversible Markov chain. We also tailor a group inverse technique to quantify the uncertainty in item ability estimates. Additionally, we prove the consistency of structure change recognition, ensuring the robustness of the proposed framework. Experiments on both synthetic and real-world datasets demonstrate the practical utility and interpretability of our approach.

The UK government is introducing a ban on social media for children and a minimum age for some chatbots in an attempt to shield young people from dangerous corners of the web. UK prime minister Keir Starmer has been leading the charge on under-16 social media regulation. Children under the age of 16 will be banned from social media platforms in the UK, under new measures announced by prime minister Keir Starmer on Monday. "The need for action could not be clearer. Social media is making our children unhappy and unsafe," said Starmer, in an X post .

Rank One, whose board includes a former CIA deputy director and a former FBI science chief, supplied face recognition to Meta for internal development of its smart glasses app. Meta is testing face-recognition software built by a company that sells surveillance tools to police departments and the United States military, as it explores bringing the technology to its smart glasses, WIRED has learned. The arrangement is documented in a software license, obtained by WIRED, that was issued by Rank One Computing--a Denver-based company that derives roughly 80 percent of its revenue from government clients--and is tied to a test version of the Meta AI app that powers Meta's Ray-Ban and Oakley smart glasses . Rank One's face recognition has been bought by the US Marshals Service, which uses it to confirm prisoners' identities without fingerprinting them during transport, and by the Naval Criminal Investigative Service--the Navy's police force--which purchased the company's video tool, ROC Watch. Rank One developed long-range face recognition for US Special Operations Command under a government research contract, saying its software could identify a face from as far as a kilometer away.

Causality in time series can be challenging to determine, especially in the presence of non-linear dependencies. Granger causality helps analyze potential relationships between variables, thereby offering a method to determine whether one time series can predict--Granger cause--future values of another.

Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging due to inter-domain interference. To overcome this challenge, we propose a partition-based multi-stage fine-tuning framework designed to exploit inter-domain synergies while minimizing negative transfer.

In this paper, we investigate the adversarial robustness of nonparametric regression, a fundamental problem in machine learning, under the setting where an adversary can arbitrarily corrupt a subset of the input data. While the robustness of parametric regression has been extensively studied, its nonparametric counterpart remains largely unexplored. We characterize the adversarial robustness in nonparametric regression, assuming the regression function belongs to the second-order Sobolev space (i.e., it is square integrable up to its second derivative). The contribution of this paper is two-fold: (i) we establish a minimax lower bound on the estimation error, revealing a fundamental limit that no estimator can overcome, and (ii) we show that, perhaps surprisingly, the classical smoothing spline estimator, when properly regularized, exhibits robustness against adversarial corruption. These results imply that if o(n) out of n samples are corrupted, the estimation error of the smoothing spline vanishes as n . On the other hand, when a constant fraction of the data is corrupted, no estimator can guarantee vanishing estimation error, implying the optimality of the smoothing spline in terms of maximum tolerable number of corrupted samples.