Reliable Chain-of-Thought via Prefix Consistency
arXiv:2605.07654v1 Announce Type: cross Abstract: Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority
Knowledge catalogue
arXiv:2605.07654v1 Announce Type: cross Abstract: Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority
arXiv:2605.07379v1 Announce Type: cross Abstract: Conventional visual object trackers localize targets using handcrafted spatial priors, often in the form of heatmaps. Such priors provide only surroga
arXiv:2510.00568v3 Announce Type: replace Abstract: Search agents powered by Large Language Models (LLMs) have demonstrated significant potential in tackling knowledge-intensive tasks. Reinforcement l
arXiv:2605.07575v1 Announce Type: cross Abstract: Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall sho
arXiv:2605.07307v1 Announce Type: new Abstract: Modern reasoning language models generate dense, sequential chain-of-thought traces implicitly assuming that every token contributes and that steps must
arXiv:2605.07331v1 Announce Type: cross Abstract: Reinforcement learning, including reinforcement learning with verifiable rewards (RLVR), has emerged as a powerful approach for LLM post-training. Cen
arXiv:2605.05806v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decode
arXiv:2605.07752v1 Announce Type: new Abstract: Semiconductor materials manufacturing presents unique challenges for machine learning deployment due to evolving process conditions, equipment degradati
arXiv:2605.08061v1 Announce Type: new Abstract: We argue that decomposing reward into weighted, verifiable criteria and using an LLM judge to score them provides a partial-credit optimization signal:
arXiv:2605.07800v1 Announce Type: new Abstract: Recent video diffusion models (VDMs) synthesize visually convincing clips, yet still drop entities, mis-bind attributes, and weaken the interactions spe
arXiv:2605.07264v1 Announce Type: new Abstract: Accurate Digital Surface Model (DSM) reconstruction from satellite imagery is critical for applications such as disaster response, urban planning, and l
arXiv:2605.07820v1 Announce Type: new Abstract: Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they u
arXiv:2605.08043v1 Announce Type: cross Abstract: While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual intents remains challenging because many
arXiv:2602.15189v2 Announce Type: replace-cross Abstract: Producing output that conforms to a specified JSON schema underlies tool use, structured extraction, and knowledge base construction in modern
arXiv:2603.05117v3 Announce Type: replace Abstract: Imitation Learning (IL) enables robots to acquire manipulation skills from expert demonstrations. Diffusion Policy (DP) models multi-modal expert be
arXiv:2605.07977v1 Announce Type: new Abstract: Recent works have advanced feedback-based learning systems, whereby a foundation model is able to intake incoming feedback (e.g., a user) to self-improv
arXiv:2605.07482v1 Announce Type: cross Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous
arXiv:2605.07711v1 Announce Type: new Abstract: On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and stude
arXiv:2605.07767v1 Announce Type: new Abstract: Poor lighting conditions significantly impact image quality, posing substantial challenges for image editing and visualization. Many existing enhancemen
arXiv:2602.03201v3 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) is sample-efficient but struggles in sparse reward settings. A critical bottleneck arises from the lack of
arXiv:2602.06283v2 Announce Type: replace Abstract: Exploiting sparsity during long-context inference is key to scaling large language models, as attention dominates the cost of autoregressive decodin
arXiv:2605.07725v1 Announce Type: cross Abstract: Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model
arXiv:2605.07301v1 Announce Type: new Abstract: Accurately predicting opponents' behavior from interactions is a fundamental capability for large language model (LLM)-based agents in multi-agent and g
arXiv:2605.07286v1 Announce Type: cross Abstract: Random-feature neural networks (RFNNs), including architectures with fixed hidden layers and analytically determined output weights, offer fast traini
arXiv:2605.08003v1 Announce Type: new Abstract: Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods
arXiv:2605.07420v1 Announce Type: cross Abstract: Pre-trained models with parameter-efficient fine-tuning (PEFT) have demonstrated promising potential for class-incremental learning (CIL), yet catastr
arXiv:2605.07116v1 Announce Type: cross Abstract: Physics-informed neural solvers offer a promising route to model-based reinforcement learning in continuous time, where optimal feedback synthesis is
arXiv:2605.08029v1 Announce Type: new Abstract: Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generat
arXiv:2605.08005v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) aims to improve time series forecasting under distribution shifts by using limited observations revealed during inference. Ho
arXiv:2605.06902v1 Announce Type: new Abstract: Adversarial robustness has been studied extensively for offline deep networks, but less is known about strict single-pass streaming neural learners. Thi
arXiv:2605.07139v1 Announce Type: cross Abstract: When distilling reasoning from large language models (LLMs) into smaller ones, teacher rationales for similar problems often vary wildly in structure
arXiv:2605.07274v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR), especially with Group Relative Policy Optimization (GRPO), has shown strong potential for improvi
arXiv:2605.07112v1 Announce Type: new Abstract: Agentic AI systems that invoke external tools are powerful but costly, leading developers to default to large models and overspend inference budgets. Mo
arXiv:2510.04839v2 Announce Type: replace Abstract: Accurate online inertial parameter estimation is essential for adaptive robotic control, enabling real-time adjustment to payload changes, environme
arXiv:2605.06886v1 Announce Type: new Abstract: This work introduces TajPersLexon, a curated Tajik--Persian parallel lexical resource of 40,112 word and short-phrase pairs for cross-script lexical ret
arXiv:2605.07256v1 Announce Type: new Abstract: Transformer architecture search (TAS) discovers optimal vision transformer (ViT) architectures automatically, reducing human effort to manually design V
arXiv:2605.07354v1 Announce Type: cross Abstract: The expanding application of smart sensing has created a growing demand for the accurate understanding of human action at the network edge. Traditiona
arXiv:2605.07237v1 Announce Type: new Abstract: Tool-integrated reasoning (TIR) has emerged as a dominant paradigm for mathematical problem solving in language models, combining natural language (NL)
arXiv:2511.12090v3 Announce Type: replace Abstract: Prompt-based continual learning methods fine-tune only a small set of additional learnable parameters while keeping the pre-trained model's paramete
arXiv:2605.05958v2 Announce Type: replace Abstract: Knowledge Tracing (KT) is fundamental to intelligent education systems, yet relies on educational logs that are selectively observed. The non-random
arXiv:2605.07078v1 Announce Type: new Abstract: Compositional generalization requires models to produce novel configurations from familiar parts. In diffusion models, prior compositional generation me
arXiv:2601.21839v2 Announce Type: replace-cross Abstract: Test-time compute has emerged as a promising strategy to enhance the reasoning abilities of large language models (LLMs). However, this strate
arXiv:2605.07282v1 Announce Type: new Abstract: Final outputs hide when a checkpoint commits to its next-token prediction. We introduce the convergence gap, a model-diffing diagnostic that decodes eac
arXiv:2605.07127v1 Announce Type: cross Abstract: Modern large language models (LLMs) can find a needle in a haystack (locating a single relevant fact buried among hundreds of thousands of irrelevant
arXiv:2602.04774v2 Announce Type: replace-cross Abstract: Setting the learning rate (LR) for a deep learning model is a critical part of successful training. Choosing LRs is often done empirically wit
arXiv:2605.07461v1 Announce Type: new Abstract: Rubrics have been extensively utilized for evaluating unverifiable, open-ended tasks, with recent research incorporating them into reward systems for re
arXiv:2510.01290v2 Announce Type: replace Abstract: The long-output context generation of large reasoning models enables extended chain of thought (CoT) but also drives rapid growth of the key-value (
arXiv:2605.06683v1 Announce Type: cross Abstract: Transformer-based large language models are in some respects limited by the quadratic time and space computational complexity of attention. We introdu
arXiv:2605.07339v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks. However, existing methods rely on a s
arXiv:2605.07677v1 Announce Type: cross Abstract: Tourism is a high-stakes setting for conversational recommender systems (CRS): a plausible-sounding suggestion can waste real money and trip time once
arXiv:2605.06966v1 Announce Type: new Abstract: Autonomous vehicles (AVs) require extensive testing in simulation, but test case generation for driving scenarios is laborious. The desired scenarios ar
arXiv:2508.10016v3 Announce Type: replace Abstract: Building interactive omni-modal assistants often relies on end-to-end multimodal alignment to fuse heterogeneous modalities, which incurs substantia
arXiv:2605.07922v1 Announce Type: new Abstract: Learning hierarchical features in Sparse Autoencoders (SAEs) is essential for capturing the structured nature of real-world data and mitigating issues l
arXiv:2509.22813v2 Announce Type: replace Abstract: State Space Models (SSMs) have emerged as efficient alternatives to Vision Transformers (ViTs), with VMamba standing out as a pioneering architectur
arXiv:2408.15339v4 Announce Type: replace-cross Abstract: RL alignment methods, including RLHF and DPO, are primarily based on pairwise preference data. Although scalar or score-based feedback has bee
arXiv:2410.06355v3 Announce Type: replace-cross Abstract: This paper presents UNCOM, a novel hybrid framework for interpreting natural human commands in tabletop scenarios. The system integrates multi
arXiv:2605.07148v1 Announce Type: new Abstract: Decades of cognitive science establish that humans navigate environments by forming cognitive maps, defined as allocentric and topology-preserving repre
arXiv:2511.03182v2 Announce Type: replace-cross Abstract: Large language models (LLMs) for code are increasingly used in software development, but they remain static after pretraining while APIs and s
arXiv:2605.06815v1 Announce Type: new Abstract: The pursuit of artificial general intelligence necessitates robust methods for evaluating the cognitive capabilities of models beyond narrow task perfor
arXiv:2605.07356v1 Announce Type: new Abstract: Semantic segmentation of large-scale 3D point clouds is crucial for applications such as autonomous driving and urban digital twins. However, the sparse