PyTorchKR Papers

최신 논문

총 2,388편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2506.09186

Not all those who drift are lost: Drift correction and calibration scheduling for the IoT

Sensors provide a vital source of data that link digital systems with the physical world. However, as sensors age, the relationship between what they measure and what they output changes. This is known as sensor drift and poses a significant challenge that, combined with limited opportunity for re-calibration, can severely limit data quality over time. Previous approaches to drift correction typically require large volumes of ground truth data and do not consider measurement or prediction uncertainty. In this paper, we propose a probabilistic sensor drift correction method that takes a fundamental approach to modelling the sensor response using Gaussian Process Regression. Tested using dissolved oxygen sensors, our method delivers mean squared error (MSE) reductions of up to 90% and more than 20% on average. We also propose a novel uncertainty-driven calibration schedule optimisation approach that builds on top of drift correction and further reduces MSE by up to 15.7%.

arXiv:2506.09998

Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling

Large language models (LLMs) can often accurately describe probability distributions using natural language, yet they still struggle to generate faithful samples from them. This mismatch limits their use in tasks requiring reliable stochasticity, such as Monte Carlo methods, agent-based simulations, and randomized decision-making. We investigate this gap between knowledge and sampling in the context of Bernoulli distributions. We introduce Verbalized Rejection Sampling (VRS), a natural-language adaptation of classical rejection sampling that prompts the LLM to reason about and accept or reject proposed samples. Despite relying on the same Bernoulli mechanism internally, VRS substantially reduces sampling bias across models. We provide theoretical analysis showing that, under mild assumptions, VRS improves over direct sampling, with gains attributable to both the algorithm and prompt design. More broadly, our results show how classical probabilistic tools can be verbalized and embedded into LLM workflows to improve reliability, without requiring access to model internals or heavy prompt engineering.

arXiv:2506.00806

Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering

Multimodal large language models (MLLMs) still struggle with complex reasoning tasks in Visual Question Answering (VQA). While current methods have advanced by incorporating visual prompts, our study uncovers critical limitations: these approaches indiscriminately annotate all detected objects for every visual question, generating excessive visual markers that degrade task performance. This issue stems primarily from a lack of focus on key visual elements, raising two important questions: Are all objects equally important, and do all questions require visual prompts? Motivated by Dual Process Theory, which distinguishes between instinctive and deliberate cognitive modes in human reasoning, we propose FOCUS, a plug-and-play approach that dynamically adapts to the complexity of questions, combining fast intuitive judgments with deliberate analytical reasoning to enhance the vision-language reasoning capability of the MLLM. For straightforward questions, FOCUS supports efficient zero-shot reasoning. For more complex tasks, it employs the conceptualizing before observation strategy to highlight critical elements. Extensive experiments on four benchmarks, ScienceQA, TextQA, VizWiz, and MME, demonstrate that FOCUS consistently improves the performance of both open-source and black-box MLLMs, achieving significant gains across all datasets. Ablation studies further validate the importance of combining diverse cognitive strategies with refined visual information for superior performance. Code will be released.

arXiv:2506.10106

One For All: LLM-based Heterogeneous Mission Planning in Precision Agriculture

Artificial intelligence is transforming precision agriculture, offering farmers new tools to streamline their daily operations. While these technological advances promise increased efficiency, they often introduce additional complexity and steep learning curves that are particularly challenging for non-technical users who must balance tech adoption with existing workloads. In this paper, we present a natural language (NL) robotic mission planner that enables non-specialists to control heterogeneous robots through a common interface. By leveraging large language models (LLMs) and predefined primitives, our architecture seamlessly translates human language into intermediate descriptions that can be executed by different robotic platforms. With this system, users can formulate complex agricultural missions without writing any code. In the work presented in this paper, we extend our previous system tailored for wheeled robot mission planning through a new class of experiments involving robotic manipulation and computer vision tasks. Our results demonstrate that the architecture is both general enough to support a diverse set of robots and powerful enough to execute complex mission requests. This work represents a significant step toward making robotic automation in precision agriculture more accessible to non-technical users.

arXiv:2506.10911공식 코드 · Papers with Code

NoLoCo: No-all-reduce Low Communication Training Method for Large Models

Training large language models is generally done via optimization methods on clusters containing tens of thousands of accelerators, communicating over a high-bandwidth interconnect. Scaling up these clusters is expensive and can become impractical, imposing limits on the size of models that can be trained. Several recent studies have proposed training methods that are less communication intensive, avoiding the need for a highly connected compute cluster. These state-of-the-art low communication training methods still employ a synchronization step for model parameters, which, when performed over all model replicas, can become costly on a low-bandwidth network. In this work, we propose a novel optimization method, NoLoCo, that does not explicitly synchronize all model parameters during training and, as a result, does not require any collective communication. NoLoCo implicitly synchronizes model weights via a novel variant of the Nesterov momentum optimizer by partially averaging model weights with a randomly selected other one. We provide both a theoretical convergence analysis for our proposed optimizer as well as empirical results from language model training. We benchmark NoLoCo on a wide range of accelerator counts and model sizes, between 125M to 6.8B parameters. Our method requires significantly less communication overhead than fully sharded data parallel training or even widely used low communication training method, DiLoCo. The synchronization step itself is estimated to be one magnitude faster than the all-reduce used in DiLoCo for few hundred accelerators training over the internet. We also do not have any global blocking communication that reduces accelerator idling time. Compared to DiLoCo, we also observe up to $4\%$ faster convergence rate with wide range of model sizes and accelerator counts.

arXiv:2506.10766

One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers

Pretraining massively multilingual Large Language Models (LLMs) for many languages at once is challenging due to limited model capacity, scarce high-quality data, and compute constraints. Moreover, the lack of language coverage of the tokenizer makes it harder to address the gap for new languages purely at the post-training stage. In this work, we study what relatively cheap interventions early on in training improve "language plasticity", or adaptation capabilities of the model post-training to new languages. We focus on tokenizer design and propose using a universal tokenizer that is trained for more languages than the primary pretraining languages to enable efficient adaptation in expanding language coverage after pretraining. Our systematic experiments across diverse groups of languages and different training strategies show that a universal tokenizer enables significantly higher language adaptation, with up to 20.2% increase in win rates compared to tokenizers specific to pretraining languages. Furthermore, a universal tokenizer also leads to better plasticity towards languages that are completely unseen in the tokenizer and pretraining, by up to 5% win rate gain. We achieve this adaptation to an expanded set of languages with minimal compromise in performance on the majority of languages included in pretraining.

arXiv:2506.05895공식 코드 · Papers with Code

Few Labels are all you need: A Weakly Supervised Framework for Appliance Localization in Smart-Meter Series

Improving smart grid system management is crucial in the fight against climate change, and enabling consumers to play an active role in this effort is a significant challenge for electricity suppliers. In this regard, millions of smart meters have been deployed worldwide in the last decade, recording the main electricity power consumed in individual households. This data produces valuable information that can help them reduce their electricity footprint; nevertheless, the collected signal aggregates the consumption of the different appliances running simultaneously in the house, making it difficult to apprehend. Non-Intrusive Load Monitoring (NILM) refers to the challenge of estimating the power consumption, pattern, or on/off state activation of individual appliances using the main smart meter signal. Recent methods proposed to tackle this task are based on a fully supervised deep-learning approach that requires both the aggregate signal and the ground truth of individual appliance power. However, such labels are expensive to collect and extremely scarce in practice, as they require conducting intrusive surveys in households to monitor each appliance. In this paper, we introduce CamAL, a weakly supervised approach for appliance pattern localization that only requires information on the presence of an appliance in a household to be trained. CamAL merges an ensemble of deep-learning classifiers combined with an explainable classification method to be able to localize appliance patterns. Our experimental evaluation, conducted on 4 real-world datasets, demonstrates that CamAL significantly outperforms existing weakly supervised baselines and that current SotA fully supervised NILM approaches require significantly more labels to reach CamAL performances. The source of our experiments is available at: https://github.com/adrienpetralia/CamAL. This paper appeared in ICDE 2025.

arXiv:2506.07814

M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration

Natural images are often degraded by complex, composite degradations such as rain, snow, and haze, which adversely impact downstream vision applications. While existing image restoration efforts have achieved notable success, they are still hindered by two critical challenges: limited generalization across dynamically varying degradation scenarios and a suboptimal balance between preserving local details and modeling global dependencies. To overcome these challenges, we propose M2Restore, a novel Mixture-of-Experts (MoE)-based Mamba-CNN fusion framework for efficient and robust all-in-one image restoration. M2Restore introduces three key contributions: First, to boost the model's generalization across diverse degradation conditions, we exploit a CLIP-guided MoE gating mechanism that fuses task-conditioned prompts with CLIP-derived semantic priors. This mechanism is further refined via cross-modal feature calibration, which enables precise expert selection for various degradation types. Second, to jointly capture global contextual dependencies and fine-grained local details, we design a dual-stream architecture that integrates the localized representational strength of CNNs with the long-range modeling efficiency of Mamba. This integration enables collaborative optimization of global semantic relationships and local structural fidelity, preserving global coherence while enhancing detail restoration. Third, we introduce an edge-aware dynamic gating mechanism that adaptively balances global modeling and local enhancement by reallocating computational attention to degradation-sensitive regions. This targeted focus leads to more efficient and precise restoration. Extensive experiments across multiple image restoration benchmarks validate the superiority of M2Restore in both visual quality and quantitative performance.

논문 ID: 3349.18402

AN INTERNSHIP REPORT ON E-HELPING HOUSING SOCIETY PROJECT REPORT

The basic concept of this society system, we create global web based application in asp.net with C# language to manage Society with House and Owner of house detail. We provide platform to register society to our system, and there are many houses according to each society. Each house allocated to owner of house, all the owner are members of our project. After becoming a member they can login to give his house on rent or sell for all users. The people can easily find search the rent house or sell house in which society and get contact detail of owner of house by visiting our website. All members can make online complain related home to society management.

arXiv:2506.06395

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

Large language models (LLMs) excel at reasoning, yet post-training remains critical for aligning their behavior with task goals. Existing reinforcement learning (RL) methods often depend on costly human annotations or external reward models. We propose Reinforcement Learning via Self-Confidence (RLSC), which uses the model's own confidence as reward signals-eliminating the need for labels, preference models, or reward engineering. Applied to Qwen2.5-Math-7B with only 16 samples per question and 10 or 20 training steps, RLSC improves accuracy by +13.4% on AIME2024, +21.2% on MATH500, +21.7% on Minerva Math, +20.8% on Olympiadbench, and +9.7% on AMC23. RLSC provides a simple, scalable post-training method for inference models, requiring only a small number of samples and unlabelled supervision.

arXiv:2506.08507

MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning

Large Language Model (LLM)-driven Multi-agent systems (Mas) have recently emerged as a powerful paradigm for tackling complex real-world tasks. However, existing Mas construction methods typically rely on manually crafted interaction mechanisms or heuristic rules, introducing human biases and constraining the autonomous ability. Even with recent advances in adaptive Mas construction, existing systems largely remain within the paradigm of semi-autonomous patterns. In this work, we propose MasHost, a Reinforcement Learning (RL)-based framework for autonomous and query-adaptive Mas design. By formulating Mas construction as a graph search problem, our proposed MasHost jointly samples agent roles and their interactions through a unified probabilistic sampling mechanism. Beyond the accuracy and efficiency objectives pursued in prior works, we introduce component rationality as an additional and novel design principle in Mas. To achieve this multi-objective optimization, we propose Hierarchical Relative Policy Optimization (HRPO), a novel RL strategy that collaboratively integrates group-relative advantages and action-wise rewards. To our knowledge, our proposed MasHost is the first RL-driven framework for autonomous Mas graph construction. Extensive experiments on six benchmarks demonstrate that MasHost consistently outperforms most competitive baselines, validating its effectiveness, efficiency, and structure rationality.

arXiv:2506.01966

Matrix Is All You Need

Deep neural networks employ specialized architectures for vision, sequential and language tasks, yet this proliferation obscures their underlying commonalities. We introduce a unified matrix-order framework that casts convolutional, recurrent and self-attention operations as sparse matrix multiplications. Convolution is realized via an upper-triangular weight matrix performing first-order transformations; recurrence emerges from a lower-triangular matrix encoding stepwise updates; attention arises naturally as a third-order tensor factorization. We prove algebraic isomorphism with standard CNN, RNN and Transformer layers under mild assumptions. Empirical evaluations on image classification (MNIST, CIFAR-10/100, Tiny ImageNet), time-series forecasting (ETTh1, Electricity Load Diagrams) and language modeling/classification (AG News, WikiText-2, Penn Treebank) confirm that sparse-matrix formulations match or exceed native model performance while converging in comparable or fewer epochs. By reducing architecture design to sparse pattern selection, our matrix perspective aligns with GPU parallelism and leverages mature algebraic optimization tools. This work establishes a mathematically rigorous substrate for diverse neural architectures and opens avenues for principled, hardware-aware network design.

arXiv:2506.00799

Uni-LoRA: One Vector is All You Need

Low-Rank Adaptation (LoRA) has become the de facto parameter-efficient fine-tuning (PEFT) method for large language models (LLMs) by constraining weight updates to low-rank matrices. Recent works such as Tied-LoRA, VeRA, and VB-LoRA push efficiency further by introducing additional constraints to reduce the trainable parameter space. In this paper, we show that the parameter space reduction strategies employed by these LoRA variants can be formulated within a unified framework, Uni-LoRA, where the LoRA parameter space, flattened as a high-dimensional vector space $R^D$, can be reconstructed through a projection from a subspace R^d, with $d \ll D$. We demonstrate that the fundamental difference among various LoRA methods lies in the choice of the projection matrix, $P \in R^{D \times d}$.Most existing LoRA variants rely on layer-wise or structure-specific projections that limit cross-layer parameter sharing, thereby compromising parameter efficiency. In light of this, we introduce an efficient and theoretically grounded projection matrix that is isometric, enabling global parameter sharing and reducing computation overhead. Furthermore, under the unified view of Uni-LoRA, this design requires only a single trainable vector to reconstruct LoRA parameters for the entire LLM - making Uni-LoRA both a unified framework and a "one-vector-only" solution. Extensive experiments on GLUE, mathematical reasoning, and instruction tuning benchmarks demonstrate that Uni-LoRA achieves state-of-the-art parameter efficiency while outperforming or matching prior approaches in predictive performance.

arXiv:2506.02553

Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective

We study a common challenge in reinforcement learning for large language models (LLMs): the Zero-Reward Assumption, where non-terminal actions (i.e., intermediate token generations) receive zero task-specific immediate reward, while only the final token receives a reward for the entire response. This assumption arises frequently in practice, as precise token-level rewards are often difficult or infeasible to obtain in LLM applications. In this work, we provide a unifying theoretical perspective. We introduce the Trajectory Policy Gradient Theorem, which shows that the policy gradient based on true, unknown token-level rewards can be unbiasedly estimated using only a response-level reward model, regardless of whether the Zero-Reward Assumption holds or not, for algorithms in the REINFORCE and Actor-Critic families. This result reveals that widely used methods such as PPO, GRPO, ReMax, and RLOO inherently possess the capacity to model token-level reward signals, offering a theoretical justification for response-level reward approaches. Our findings pave the way for more practical, efficient LLM fine-tuning, allowing developers to treat training algorithms as black boxes and focus on improving the response-level reward model with auxiliary sub-models. We also offer a detailed analysis of popular RL and non-RL methods, comparing their theoretical foundations and practical advantages across common LLM tasks. Finally, we propose a new algorithm: Token-Reinforced Policy Optimization (TRePO), a theoretically grounded method that is simpler than PPO, matches GRPO in memory efficiency, and holds promise for broad applicability.

arXiv:2506.04742

Was Residual Penalty and Neural Operators All We Needed for Solving Optimal Control Problems?

Neural networks have been used to solve optimal control problems, typically by training neural networks using a combined loss function that considers data, differential equation residuals, and objective costs. We show that including cost functions in the training process is unnecessary, advocating for a simpler architecture and streamlined approach by decoupling the optimal control problem from the training process. Thus, our work shows that a simple neural operator architecture, such as DeepONet, coupled with an unconstrained optimization routine, can solve multiple optimal control problems with a single physics-informed training phase and a subsequent optimization phase. We achieve this by adding a penalty term based on the differential equation residual to the cost function and computing gradients with respect to the control using automatic differentiation through the trained neural operator within an iterative optimization routine. We showcase our method on nine distinct optimal control problems by training three separate DeepONet models, each corresponding to a different differential equation. For each model, we solve three problems with varying cost functions, demonstrating accurate and consistent performance across all cases.

arXiv:2506.04446

Selective Matching Losses -- Not All Scores Are Created Equal

Learning systems match predicted scores to observations over some domain. Often, it is critical to produce accurate predictions in some subset (or region) of the domain, yet less important to accurately predict in other regions. We construct selective matching loss functions by design of increasing link functions over score domains. A matching loss is an integral over the link. A link defines loss sensitivity as function of the score, emphasizing high slope high sensitivity regions over flat ones. Loss asymmetry drives a model and resolves its underspecification to predict better in high sensitivity regions where it is more important, and to distinguish between high and low importance regions. A large variety of selective scalar losses can be designed with scaled and shifted Sigmoid and hyperbolic sine links. Their properties, however, do not extend to multi-class. Applying them per dimension lacks ranking sensitivity that assigns importance according to class score ranking. Utilizing composite Softmax functions, we develop a framework for multidimensional selective losses. We overcome limitations of the standard Softmax function, that is good for classification, but not for distinction between adjacent scores. Selective losses have substantial advantage over traditional losses in applications with more important score regions, including dwell-time prediction, retrieval, ranking with either pointwise, contrastive pairwise, or listwise losses, distillation problems, and fine-tuning alignment of Large Language Models (LLMs).

arXiv:2506.04734

Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design

Reasoning models represented by the Deepseek-R1-Distill series have been widely adopted by the open-source community due to their strong performance in mathematics, science, programming, and other domains. However, our study reveals that their benchmark evaluation results are subject to significant fluctuations caused by various factors. Subtle differences in evaluation conditions can lead to substantial variations in results. Similar phenomena are observed in other open-source inference models fine-tuned based on the Deepseek-R1-Distill series, as well as in the QwQ-32B model, making their claimed performance improvements difficult to reproduce reliably. Therefore, we advocate for the establishment of a more rigorous paradigm for model performance evaluation and present our empirical assessments of the Deepseek-R1-Distill series models.

arXiv:2506.04803공식 코드 · Papers with Code

SupeRANSAC: One RANSAC to Rule Them All

Robust estimation is a cornerstone in computer vision, particularly for tasks like Structure-from-Motion and Simultaneous Localization and Mapping. RANSAC and its variants are the gold standard for estimating geometric models (e.g., homographies, relative/absolute poses) from outlier-contaminated data. Despite RANSAC's apparent simplicity, achieving consistently high performance across different problems is challenging. While recent research often focuses on improving specific RANSAC components (e.g., sampling, scoring), overall performance is frequently more influenced by the "bells and whistles" (i.e., the implementation details and problem-specific optimizations) within a given library. Popular frameworks like OpenCV and PoseLib demonstrate varying performance, excelling in some tasks but lagging in others. We introduce SupeRANSAC, a novel unified RANSAC pipeline, and provide a detailed analysis of the techniques that make RANSAC effective for specific vision tasks, including homography, fundamental/essential matrix, and absolute/rigid pose estimation. SupeRANSAC is designed for consistent accuracy across these tasks, improving upon the best existing methods by, for example, 6 AUC points on average for fundamental matrix estimation. We demonstrate significant performance improvements over the state-of-the-art on multiple problems and datasets. Code: https://github.com/danini/superansac

arXiv:2506.04421

HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation

Visual Auto-Regressive modeling (VAR) has shown promise in bridging the speed and quality gap between autoregressive image models and diffusion models. VAR reformulates autoregressive modeling by decomposing an image into successive resolution scales. During inference, an image is generated by predicting all the tokens in the next (higher-resolution) scale, conditioned on all tokens in all previous (lower-resolution) scales. However, this formulation suffers from reduced image quality due to the parallel generation of all tokens in a resolution scale; has sequence lengths scaling superlinearly in image resolution; and requires retraining to change the sampling schedule. We introduce Hierarchical Masked Auto-Regressive modeling (HMAR), a new image generation algorithm that alleviates these issues using next-scale prediction and masked prediction to generate high-quality images with fast sampling. HMAR reformulates next-scale prediction as a Markovian process, wherein the prediction of each resolution scale is conditioned only on tokens in its immediate predecessor instead of the tokens in all predecessor resolutions. When predicting a resolution scale, HMAR uses a controllable multi-step masked generation procedure to generate a subset of the tokens in each step. On ImageNet 256x256 and 512x512 benchmarks, HMAR models match or outperform parameter-matched VAR, diffusion, and autoregressive baselines. We develop efficient IO-aware block-sparse attention kernels that allow HMAR to achieve faster training and inference times over VAR by over 2.5x and 1.75x respectively, as well as over 3x lower inference memory footprint. Finally, HMAR yields additional flexibility over VAR; its sampling schedule can be changed without further training, and it can be applied to image editing tasks in a zero-shot manner.