paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Sparse and robust geometric twin support vector machine via asymmetric RoBoSS loss function

Kai Qi, Xinji Huang, Hongchun Wang

In real-world scenarios, the training data usually contains redundant features, label noise and feature noise, which provide severe challenges for the efficiency of machine learning methods. Since standard support vector machine (SVM) adopts $l_2$-norm penalty and hinge loss function, it lacks the ability of selecting significant features and is sensitive to noise. To address these issues, this paper proposes a novel asymmetric, robust, bounded, sparse and smooth (aR) loss function for $l_1$-norm penalized geometric twin SVM (aRSGTSVM) to handle classification and regression tasks. The $l_1$-norm penalty can achieve the feature selection. The proposed aR loss function can not only effectively mitigate the impact of label noise, but also significantly enhance the stability to resampling noise, i.e., the zero-mean feature noise around the boundary hyperplanes. Furthermore, a statistical analysis of the robustness of aRSGTSVM was also conducted using the influence function. Since aRSGTSVM involves nonconvex and nonsmooth optimization, we develop a fast and stable proximal gradient descent based solving algorithm. Compared with related state-of-the-art methods, experimental results demonstrate the superiority of the proposed aRSGTSVM on both synthetic and UCI datasets. Furthermore, we apply aRSGTSVM to index tracking tasks, where results for tracking the different indices in the China stock market show that it can achieve satisfactory performance.

arXiv

When Offline Evaluation Misleads: A Diagnostic Protocol for Reward and Policy Selection in Delayed-Feedback Contextual Bandits

Sang Su Lee, Vineeth Loganathan, Shishir Dash, Vijay Raghavan

Personalizing marketing messages with contextual multi-armed bandits (CMABs) drives real business value, yet the objective that ultimately matters - a downstream conversion - is observed only weeks later, too late to drive online learning. Teams therefore train the bandit on a fast proxy reward, and separately must judge whether a contextual bandit is worth its complexity over sending one best message. Settling both decisions with the usual offline checks - a batch off-policy estimate, a marginal arm-discrimination test, a confidence interval - can mislead systematically under delayed feedback. We give an ordered diagnostic protocol that screens a reward-and-policy candidate on two axes, alignment (does optimizing the reward move the north-star?) and learnability (can the bandit identify the reward-optimal policy?), before trusting any reported lift. We validate it where the truth is known - a public off-policy-evaluation benchmark and a controllable synthetic generator - and illustrate it on a deployed large-marketplace push system (where, with five arms and one split, the evidence is directional rather than powered). Two lessons recur. (N1) A single offline number can mis-rank rewards: a denser reward signal gives the bandit more to learn from, so rewards that look tied in a static estimate pull apart once learning happens online. (N2) If you cannot tell in advance which single message is best, a per-user policy partly just avoids betting on the wrong one - that looks like personalization but is really robustness, so a "personalization premium" is easily overstated. Our contribution is methodological rather than algorithmic: the ordered protocol, the two lessons it surfaces, and the end-to-end experience of applying it to a delayed-feedback CMAB.

arXiv

Certifying What Helps Customer-Return Timing: A Screen-and-Confirm Test for Conditioning Signals, and Why Decay Is Nearly Enough

Sang Su Lee, Vineeth Loganathan, Shishir Dash, Vijay Raghavan

Practitioners enrich customer-return models with ever more signals (lifetime value, category, recency/frequency, calendar, geography), and the temporal-point-process (TPP) literature follows suit with covariate- and external-covariate-conditioned intensities. But does any of it improve the timing, and how would you know? A null ("feature X doesn't help") is only meaningful if the model could have found a signal. We make two contributions--a method and a measurement--to answer this credibly. (i) A screen-and-confirm protocol that certifies whether a candidate signal improves a TPP's event-timing likelihood: a positive control plants a coupling of known strength and confirms the model recovers it, so a real-data null can be read as "no signal" rather than "weak method." The control is validated for categorical and continuous encodings, and on a real clock-driven dataset (NYC taxi hour-of-day). (ii) A model-free ceiling quantifying how little of customer-return timing is point-predictable at all (a single-digit percentage of gap variance from any covariate; returns are near-memoryless). With these we certify a clean result on three public benchmarks (Amazon, Taobao, RetailRocket) and a real marketplace (Thumbtack): the inter-event clock--continuous-time decay, long known to beat frozen-intensity models--is nearly sufficient, and the conditioning the field keeps adding is redundant or harmful on top of it (statistically null on the public benchmarks, at most 0.06 NLL; null to mildly harmful on the marketplace). We do not claim to discover that decay helps; our contribution is the tools that turn "conditioning doesn't help" into a checkable, certified statement--plus an honest-evaluation account of the read-out/leakage pitfalls we hit and retracted.

arXiv

Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows

Thejani Gamage, Hyemin Gu, Zhizhen Zhang, Ziyu Chen, Markos Katsoulakis, Luc Rey-Bellet

We propose CVaR-penalized Generative Particle Algorithm (CVaR-GPA), a robust, tail-agnostic algorithm for fine-tuning generative models to learn heavy-tailed distributions and capture extreme events, requiring no prior knowledge or estimation of the target's tail characteristics. The method is the Wasserstein gradient flow of the Lipschitz-regularized Kullback-Leibler (KL) divergence penalized by a Conditional Value-at-Risk (CVaR) discrepancy term: the Lipschitz-regularized KL divergence enables robust learning under minimal assumptions on the target distribution, while the CVaR penalty restores the velocity that otherwise vanishes prematurely in the under-sampled tails. The penalized flow admits a bounded but non-Lipschitz velocity field. This departs from the Lipschitz transport maps of standard generators, which preserve the tail behavior of a light-tailed source, and enables transport toward heavier-tailed targets. To define this flow on empirical measures, we derive the first-variation subgradients of CVaR from its Rockafellar-Uryasev representation, valid precisely where the classical density-based formula fails. The particle algorithm CVaR-GPA fine-tunes the output samples of any pre-trained model, without access to its architecture, and runs on an adaptive time horizon set by a kinetic-energy stopping criterion rather than a preset depth. On synthetic isotropic and anisotropic Student-$t$ target distributions, Neal's funnel distribution, and the real-world high-dimensional Fama-French 25 portfolio dataset, CVaR-GPA dramatically improves global and tail accuracy on heavy-tailed targets over the pre-trained baseline.

arXiv

Robust Ambiguity Detection (RAD) From Model- and Feature-Space Consistency

Manya Singh, Mark T. Keane, Arjun Pakrashi

Machine learning models should be robust, in the sense of remaining predictively consistent under permissible variations. A model's predictions should ideally remain unchanged when it is replaced by a functionally equivalent one, or when its inputs are subject to minor, admissible perturbations. If such changes alter a prediction significantly, then the prediction is "ambiguous" with respect to the model. Models should abstain from making such ambiguous predictions and/or should flag them for human inspection, especially in high-stakes decision-making scenarios. However, in practice, such ambiguity is not easy to identify once a model is deployed. Here, the Robust Ambiguity Detection (RAD) framework is advanced for quantifying predictive ambiguity using two complementary metrics: Model-Space Consistency and Feature-Space Consistency. These two scores, the RAD Score-Pair, visualised through the RAD Plot, provide an interpretable characterisation of the sources of ambiguity and the actions a user may consider in response. RAD is evaluated on synthetic datasets with systematically controlled overlap, as well as several real-world datasets where the level of ambiguity cannot be directly inspected. Finally, we demonstrate a downstream application of RAD where samples are ranked by their RAD Pareto-Rank and the most ambiguous are abstained from prediction, achieving performance comparable to existing rejection-based approaches.

arXiv

Hierarchical Federated Transfer Learning in Digital Twin-Based Vehicular Networks

Qasim Zia, Saide Zhu, Haoxin Wang, Zafar Iqbal, Yingshu Li

In recent research on the Digital Twin-based Vehicular Ad hoc Network(DT-VANET), Federated Learning (FL) has shown its ability to provide data privacy. However, Federated learning struggles to adequately train a global model when confronted with data heterogeneity and data sparsity among vehicles, which ensure suboptimal accuracy in making precise predictions for different vehicle types. To address these challenges, this paper combines Federated Transfer Learning (FTL) to conduct vehicle clustering related to types of vehicles and proposes a novel Hierarchical Federated Transfer Learning (HFTL). We construct a framework for DT-VANET, along with two algorithms designed for cloud server model updates and intra-cluster federated transfer learning, to improve the accuracy of the global model. In addition, we developed a data quality score-based mechanism to prevent the global model from being affected by malicious vehicles. Lastly, detailed experiments on real-world datasets are conducted, considering different performance metrics that verify the effectiveness and efficiency of our algorithm.

arXiv

FLARE++: Low-rank attention with dynamic attention routing

Vedant Puri, Yongjie Jessica Zhang, Levent Burak Kara

Full self-attention is a strong token mixer for PDE surrogates on irregular domains, but its quadratic cost limits its use on high-resolution problems. Efficient latent-attention models such as the Fast Low-rank Attention Routing Engine (FLARE) avoid that cost by routing all N tokens through M << N learned latent queries, but those queries are parameters: once trained, the same learned query templates serve every input. We remove this restriction with FLARE++, a low-rank attention architecture with dynamic token routing. FLARE++ reuses FLARE's own encoder to build its routing queries: learned latent seeds drive one extra encode call that gathers the N input tokens into M input-conditioned queries, and those queries then determine how the same tokens are compressed and redistributed. This preserves FLARE's explicit low-rank factorization and linear O(NM) complexity, and expresses the complete routing operation with standard scaled dot-product attention (SDPA) calls alone. We also provide a multi-GPU context-parallel implementation that shards input tokens across devices without ever gathering the full token sequence on one of them. FLARE++ is competitive across a set of standard PDE surrogate benchmarks, improving on fixed-query FLARE by 24% on average, and it gains 2.3 points of average accuracy on Long Range Arena.

arXiv

Do Judges Behave Like Algorithms?

Riya Manchanda, Eric Chen, Chloe Zhu, Cynthia Rudin, Brandon Garrett, Songman Kang

What if judges already behave like algorithms? As artificial intelligence and algorithms are deployed in many settings, including the judicial system, many have debated whether judges should be allowed to rely on them. Instead, we ask whether judges follow predictable, algorithmic-like rules already. If judges already follow consistent, formula-like rules based on discrete and static factors such as criminal history, age, and charge type, then judicial behavior may be improved. However, if judges rely on individualized information that cannot be identified through court data, then standards-based decision-making may be more challenging to understand or improve. This work explores these questions by studying judicial decision-making in misdemeanor bail hearings in Harris County, Texas. Using available court data, we investigate whether magistrate judges follow what resembles an algorithm; whether they consider the same variables in their decision-making; and whether they are consistent with themselves and with each other. To do this, we train machine learning models for each judge, measure variable importance metrics to determine important variables for each judge's decision-making, and analyze outcomes of similar cases for judges. Our results reveal that these judges generally behave algorithmically: their decisions can be captured by small, interpretable formulas. However, in some cases, judges differ substantially, leading to surprising inconsistency and unequal treatment across similar defendants. Identifying cases where algorithms do not explain judicial decision-making can improve the justice system by focusing attention on decisions where individualized standards, rather than rules, better explains outcomes.

arXiv

Logit-Boundary Geometric Belief Interfaces and Sparse Sheaf-Enclave Protocols: A Self-Contained Substrate for Secure Network Electronic Health Record (EHR) Interoperability

Alvin Spivey, Yu Huang

Electronic health-record interoperability is a boundary problem: legacy systems, generative models, terminology services, identity systems, and human reviewers may each expose rich internal states, while operational exchange requires a narrow shared interface of typed claims, bounded uncertainty, provenance, and explicit admission or abstention. This paper details a mathematical and engineering architecture for that interface. The organizing idea is the logit boundary: a discovery model may propose pre-threshold scores over a local categorical decision, but a deterministic judgment substrate decides whether the proposal is admissible, requires review, or must be quarantined before any Fast Healthcare Interoperability Resources (FHIR) transaction is constructed. The resulting Geometric Belief Interface (GBI) combines finite boundary semantics, local Dirichlet evidence, cellular-sheaf and mapping-cone diagnostics, advisory geometric audit charts, and a Decentralized Cryptographic Sheaf-Enclave (DCSE) protocol sketch for fail-closed deployment. The framework does not establish clinical truth, global representation alignment, or end-to-end safety; it defines certificate-producing checks at a model-to-system boundary. A companion frozen synthetic benchmark, GBI BoundaryBench v0.1, evaluated Qwen3-4B-Instruct-2507 on 256 held-out tasks across three evidence modes (768 canonical executions). All executions completed, but none produced an output accepted by the benchmark contract: 369 were rejected during safe parsing and 399 during schema validation, yielding zero coverage and deterministic quarantine. This empirical result is deliberately narrow - one 4B open-weight model under one frozen interface - and is reported as evidence about the admission boundary, not as a general claim about LLM capability or clinical safety. A Julia appendix verifies numerical certificates using standard libraries.

arXiv

CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models

Ye Qiao

Low-precision formats usually optimize scalar fidelity while inheriting conventional product arithmetic. We introduce CurveFP, a block-scaled family that distributes magnitudes across interleaved logarithmic curves. Uniform curve indices make every nonzero product an exact sign and integer-index update, while a rational radix exposes the finite phase schedule required for accumulation. We instantiate the algebra as CurveFP8 E4C3/E5C2 for training and CurveFP7 E3C3 for compact inference. On four 7B-9B models, CurveFP7 beats tensorwise FP8 perplexity with one fewer element bit and stays within 1.32% of native quality. CurveFP8 lowers error in all 36 paired training-GEMM comparisons. Across three matched 3B-token pretraining triplets, it reaches mean BF16-inference perplexity 22.5366 versus 22.5407 for FP8 and has a lower format penalty in every seed. Downstream evaluation shows transfer parity and a consistent WikiText-103 gain. In a preliminary 4x4 Nangate45 spatial accelerator tile, CurveFP8 uses one fewer product register and 4.6% less area than timing-closing FP8 at 500 MHz. These results support CurveFP as a numerical and arithmetic co-design, while leaving system-level efficiency to future study.

arXiv

Causal State-Space Model for Causal Inference: Estimating Longitudinal Individual Treatment Effects

Abisoye Abidakun, Mingjun Zhong, Georgios Leontidis

Estimating counterfactual outcomes over time from longitudinal observational data is central to clinical decision support. Existing methods rely on domain confusion -- adversarial training that renders representations invariant to treatment assignment -- yet this invariance creates a mutual information conflict: it suppresses treatment-correlated covariate signals necessary for accurate outcome prediction. We formalise this tension via a Jensen-Shannon divergence bound on counterfactual prediction error and develop two complementary models. CSSD (Causal State-Space model with Direct decoder) adapts selective State Space Models with a parallel multi-step decoder that eliminates accumulated rollout error by producing all prediction horizons simultaneously in a single forward pass. CSSPD (Causal State-Space model with Predictive regularisation and Direct decoder) augments CSSD with Contrastive Predictive Coding and Local Information Maximisation to reinforce temporal predictability in the balancing representation and recover local covariate information destroyed by domain confusion. On MIMIC-III, CSSPD achieves lower counterfactual RMSE than the Causal Transformer at every horizon tau >= 2 at O(T) encoder cost, with gains from 0.02 (2-step) to 0.07 (6-step). On Cancer Simulation across confounding strengths gamma in {0,1,2,3,4}, CSSPD outperforms CT at gamma <= 3 (margins 25.9%--37.0%), and CSSD achieves the lowest overall average RMSE (12.7% reduction over CT), confirming the MI conflict analysis. To our knowledge, this is the first work to formalise the balancing-prediction MI conflict and propose a structured resolution through complementary predictive and information-theoretic training objectives.

arXiv

Continual Learning in Transition

Zhiyan Hou, Dan Zhang, Tao Feng, Liyuan Wang, Wei Li, Xiangzhao Hao, Hongyan An, Junfeng Fang, Haokai Ma, Zhaohui Xu, Xinyu Tang, Haiyun Guo, Jinqiao Wang, Tat-Seng Chua

Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architectural designs, and weight adaptation. However, emerging paradigms are reshaping the scope of CL beyond this traditional model adaptation view. For instance, on-policy learning broadens the space of update mechanisms; test-time training extends CL from the training phase to inference; and external harness components such as memory, skill libraries, and interaction protocols extend the evolutionary boundaries of model capabilities far beyond the static parameter space. Collectively, these developments indicate a transition from parameter-centric learning toward system-level adaptation. To characterize this transition, we examine the evolution of continual learning through three dimensions: When, How, and Where learning occurs. The How dimension encompasses off-policy, on-policy, and beyond-gradient optimization mechanics. The When dimension captures evolution across pre-training, post-training, and inference-time stages. The Where dimension delineates updates occurring within internal parameters versus external structural constraints. Anchored by this tri-axial framework, we systematically survey representative methods, trace the ongoing transition of continual learning, and discuss the key challenges, broader implications, and future directions arising from this paradigm shift.

arXiv

Unscented KalmanNet: Structure-Preserving Deep Learning with Calibrated Posterior Uncertainty under Incomplete Physics and Unknown Noise

Minhyeok Ko, Abdollah Shafieezadeh

Nonlinear state estimation requires sequentially fusing model-based predictions with noisy measurements. Under imperfect dynamics and unknown, time-varying noise statistics, this fusion can degrade in both accuracy and statistical consistency. Existing learning-aided filters largely treat accuracy and uncertainty estimation separately, limiting their ability to correct model-mismatch-induced bias while retaining an explicit, calibrated posterior covariance. This paper introduces Unscented KalmanNet (UKN), a model-based deep learning architecture that extends the Unscented Kalman Filter (UKF) with learned mechanisms for these two sources of filtering error while preserving explicit posterior covariance propagation. NoiseNet learns time-varying process and measurement covariances as bounded multiplicative corrections to baseline covariances, guaranteeing positive definiteness, while GainNet learns a bounded residual correction to the analytical UKF gain to compensate for model-mismatch-induced bias. A calibration-aware training objective couples state error with posterior covariance and innovation consistency terms through adaptive weighting, jointly optimizing accuracy and calibration. UKN is benchmarked against UKF, KalmanNet, and Bayesian KalmanNet on three synthetic systems and real-flight UZH-FPV data. It achieves the lowest state-estimation error in all four examples and reduces RMSE by 26.4-49.7% compared with UKF in the synthetic cases. Leave-one-sequence-out cross-validation over 11 flights shows 22.4% and 34.3% reductions in mean position and velocity RMSE, respectively. UKN also yields the lowest fold-to-fold variability, with dimension-normalized NEES and empirical coverage closest to nominal values among covariance-reporting filters. These results show that structured learned adaptation improves estimation accuracy while retaining calibrated uncertainty.

arXiv

Empowering Credit Risk Detection in Weixin Pay with Billion-Scale Deep Graph Learning

Xin Liu, Xiyuan Chen, Chenglong Wu, Xuan Zong, JUN ZHOU, Dawei Cheng

Credit risk detection, particularly mitigating individual fraud, is crucial for maintaining the stability of digital financial ecosystems. Accurately identifying credit fraud among billions of users is critical for minimizing financial losses and safeguarding the sustainability of inclusive financial services. Given that credit fraud risks are often concealed within heterogeneous user-risk graphs, Graph Neural Networks (GNNs) have emerged as an effective tool for risk mining by capturing complex dependencies. To address the scalability bottleneck of industrial GNNs, distributed training based on subgraphs is indispensable. However, existing strategies often compromise topological integrity for load balancing. This can be catastrophic for risk detection, as it indiscriminately severs the long-tail evidence chains essential for risk propagation. Overlapping subgraphs can restore severed risk contexts but inevitably introduce redundancy and noise, while overlooking the representation alignment across different local subgraphs. In this paper, we propose a risk-aware overlapping subgraph learning framework for large-scale credit risk detection. We first construct base partitions to ensure load balance. Then, we perform budget-constrained sampling that selects informative long-tail nodes, thereby preserving critical risk diffusion patterns while filtering out noise. To mitigate representation inconsistency, we design a cross-subgraph consistency alignment mechanism. By enforcing alignment constraints on the overlapping nodes, we harmonize the local representations into a globally consistent latent space. Extensive experiments on Weixin Pay's production dataset demonstrate that our model significantly outperforms existing strategies for risk detection, offering a scalable and effective solution for industrial graph learning.

arXiv

DREvo: Distilling Recalibrated Historical Experience for Harness Self-Evolution

Hanghui Guo, Weijie Shi, Zhangze Chen, Shengxiang Xu, Yishu Wang, Yimei Zhang, Wangze Ni, Jia Zhu, Shimin Di

Harness plays a critical role in large language model agent performance, and building a high-performing harness requires substantial expert effort. Therefore, recent research has increasingly explored harness self-evolution, which iteratively proposes, evaluates, and improves harnesses using historical trial experience. However, accumulated historical experience does not always translate into stable search guidance, and performance often fluctuates substantially across evolution iterations, making it difficult to reliably discover high-performing harnesses under a limited evolution budget. We identify two limitations in how existing harness self-evolution methods leverage historical experience: (1) Lack of dynamic reassessment of whether historical experience remains valid for the current harness, and (2) Lack of explicit mechanisms for translating valid historical experience into actionable search directions. To address these limitations, we propose a new harness self-evolution method, named DREvo, which integrates function-level evidence anchoring, state-dependent evidence recalibration, and role-conditioned search intent distillation to determine which historical evidence remains valid and where the harness should evolve next. Under limited evolution budgets, DREvo exhibits smoother evolution trajectories, achieves the highest accuracy on all five benchmarks, and delivers average gains of 16.2% and 14.2% over the evaluated baselines on domain reasoning and agentic tasks, respectively.

arXiv

PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation

Shaoheng Xu, Chunyi Sun, Jihui Zhang, Amy Bastine, Prasanga N. Samarasinghe, Thushara D. Abhayapala

Image-source-method (ISM)-based room impulse response (RIR) simulation is a useful and physically interpretable tool for acoustic scene modeling, but full-order ISM becomes computationally expensive as the reflection order and room complexity increase. We propose a physics-guided framework for fast RIR simulation that preserves the geometric structure of ISM while learning to retain only acoustically important image-source paths during online traversal. To recover energy removed by pruning, the proposed PathRIR uses a lightweight compensation multilayer perceptron to predict the missing late-tail energy envelope and generate a compensation tail whose energy follows that envelope. Experiments on irregular 3D rooms show that PathRIR reduces image-source computation and improves runtime efficiency over a full-order ISM simulator, while achieving low waveform- and decay-related errors. Ablation results show that adding the compensation tail improves waveform fidelity and reduces energy-decay-curve error, reverberation-time error, and direct-to-reverberant-ratio error, with modest runtime overhead.

arXiv

OrderMoE: An expert similarity driven distributed edge MoE inference

Xin Yuan, Ning Li, Quan Chen, Wenchao Xu, Song Guo

Although mixture-of-experts, MoE, models have been increasingly adopted to scale large language models with moderate computation cost, it remains challenging to deploy MoE inference over resource-constrained and bandwidth-limited edge infrastructures. Existing distributed MoE serving methods mainly rely on exact expert placement, caching, replication, or communication scheduling, while overlooking the functional similarity among experts, which provides an opportunity to reduce cross-server token transmission. Therefore, this paper introduces a similarity-aware expert allocation and distributed deployment framework, dubbed OrderMoE, which aims to accelerate edge MoE inference while balancing inference latency, communication overhead, server workload, and inference quality. OrderMoE first constructs an expert similarity model based on router-induced logits representations and partitions experts in each MoE layer into multiple similarity groups. Then, it develops a similarity-aware expert grouping and deployment strategy to improve local similarity coverage across edge servers. Since reducing remote expert invocation and preserving exact inference quality are conflicting objectives, OrderMoE further designs a quality-aware and trajectory-aware runtime server-expert selection algorithm to decide whether a token should invoke its remote target expert or use a feasible local substitute expert. Experimental results on a real distributed edge testbed show that OrderMoE significantly reduces average latency, tail latency, cross-server traffic, and remote expert invocation ratio, while introducing only small and controllable inference quality degradation.

arXiv

Reducing Per-Sample Interference in Stochastic Optimization

Apostolos Avranas

Modern optimizers combine gradients from the current mini-batch with historical optimization state, such as momentum or adaptive moments. While effective, this standard practice can produce parameter updates that actively increase the loss of individual samples. We term this phenomenon per-sample interference and propose redefining the parameter update as an optimization problem that explicitly minimizes it. Because the exact formulation of the problem is computationally prohibitive, we introduce a highly efficient surrogate. By reducing the problem's dimensionality to the batch size and restricting the optimization to the last linear layer, we overcome memory and speed bottlenecks. This strategy hinges on our unexpected finding that this layer alone can reliably capture core second-order statistics of the full network. The resulting surrogate problem integrates readily into standard optimizers like SGD and AdamW, and can be solved using a small number of GPU-friendly iterations. Crucially, the method exhibits favorable scaling properties, as the relative computational overhead shrinks as the model size or input grows. Experiments on image classification benchmarks confirm reduced per-sample interference and improved generalization.

arXiv

Gauge-Fixing the Forward-Forward Objective: A Whitened Goodness Derived from a Likelihood-Ratio Account

Paolo Giannitrapani

The Forward-Forward algorithm trains each layer locally, so that a scalar goodness - the sum of squared activations - is high on real inputs and low on contrastive ones. Under an explicit generative model this goodness is the sufficient statistic of a likelihood-ratio test, and the pairwise form of the objective admits a gauge: a layer can lower its loss by inflating the scale of its weights rather than by separating the two populations. The analysis prescribes the repair - a whitened, scale-invariant goodness trained online within each layer - which we evaluate as a training procedure. Across three corpora, three depths and a fourfold range of layer width (13 seeds per cell), it raises linear-probe accuracy over the standard pairwise objective in every measured cell - by 4 to 7 points on eight of nine corpus-depth combinations - and closes 16-61% of the gap to end-to-end backpropagation. A control isolates the mechanism: Hinton's fixed-threshold loss also bounds the runaway, to a factor of 1.4 against 133, yet tracks the unmodified baseline - invariance to the gauge, not a bound on it, is what pays. Against the strongest published alternative - a sparse, top-k goodness - the derived objective is statistically indistinguishable on two corpora of three, yet only it removes the runaway: sparsity and gauge-invariance are independent axes, and the published variant recovers accuracy while leaving the pathology in place. We state the boundaries we measured, and every prediction was recorded before its experiment with the refutations reported.

arXiv

Prompt-Driven Exploration

Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong

Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such jitter only yields rollouts close to the original. Escaping a weak policy often requires global perturbations that action noise cannot produce. Large language models (LLMs) and vision-language-action (VLA) models offer a pathway: they condition the policy on a natural language prompt, and since the rollout follows from it, modifying the prompt induces global changes. The challenge is finding prompts that induce useful global changes. With a weak policy that rarely succeeds, reward is too sparse to select on. Our idea is to refine prompts from the rollouts themselves: a vision-language model (VLM) reasons over the rollout video, diagnoses how the policy responded, and rewrites the prompt to elicit better behavior next time. This procedure resembles posterior sampling, a classical RL exploration framework, at the level of prompts: the VLM maintains an implicit distribution over useful prompts and updates it from observed rollouts. We call this strategy Prompt-Driven Exploration (PDE). Across manipulation and reasoning tasks, PDE enables RL to learn successful policies even from zero-reward starts, and improves sample efficiency more broadly. Our website is available at https://xinyunsunshine.github.io/prompt-rl.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.