arXiv:2605.04215v2 Announce Type: replace-cross Abstract: Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead to significant throughput advantages and superior GPU utilization over the traditional autoregressive paradigm. However, this parallelism is constrained by the requirement of a fixed-size response length prior to generation. This […]
MultiEmo-Bench: Multi-label Visual Emotion Analysis for Multi-modal Large Language Models
arXiv:2605.14635v1 Announce Type: cross Abstract: This paper introduces a multi-label visual emotion analysis benchmark dataset for comprehensively evaluating the ability of multimodal large language models (MLLMs) to predict the emotions evoked by images. Recent user studies report an unintuitive finding: humans may prefer the predictions of MLLMs over the labels in existing datasets. We argue […]
Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learning
arXiv:2605.07799v2 Announce Type: replace-cross Abstract: Training foundation models is computationally intensive and often slow to converge. We introduce PIQL,Privileged Information for Quick and Quality Learning, the first framework to systematically integrate privileged information (PI) to simultaneously accelerate learning and improve generalization in tabular foundation models (TFMs). We construct two complementary forms of PI: (i) aggregate […]
Learning, Fast and Slow: Towards LLMs That Adapt Continually
arXiv:2605.12484v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of plasticity. In contrast, in-context learning with fixed LLM parameters can cheaply and rapidly adapt to task-specific […]
Action-Inspired Generative Models
arXiv:2605.14631v1 Announce Type: cross Abstract: We introduce Action-Inspired Generative Models (AGMs), a dual-network generative framework motivated by the observation that existing bridge-matching methods assign uniform regression weight to every stochastic transition in the transport landscape, regardless of whether a given bridge sample lies along a structurally coherent trajectory or a degenerate one. We address this […]
Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training
arXiv:2605.14773v1 Announce Type: cross Abstract: Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly focus on designing sample-importance criteria, i.e., deciding what to select, while typically fixing the selected data volume as the target ratio throughout training. Thus, they are often dynamic in sample identity but static […]
Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
arXiv:2605.12394v2 Announce Type: replace-cross Abstract: Training Neural Networks (NNs) without overfitting is difficult; detecting that overfitting is difficult as well. We present a novel Random Matrix Theory method that detects the onset of overfitting in deep learning models without access to train or test data. For each model layer, we randomize each weight matrix element-wise, […]
Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations
arXiv:2605.14937v1 Announce Type: cross Abstract: Predictive world models enable agents to model scene dynamics and reason about the consequences of their actions. Inspired by human perception, object-centric world models capture scene dynamics using object-level representations, which can be used for downstream applications such as action planning. However, most object-centric world models and reinforcement learning (RL) […]
AI Knows When It’s Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models
arXiv:2605.15034v1 Announce Type: cross Abstract: Large language models (LLMs) have been extensively studied from computational and cognitive perspectives, yet their behavior as communicative actors in socially structured contexts remains underexplored. This study examines whether LLM-based multi-agent systems exhibit systematic linguistic adaptation in response to perceived social observation contexts — a question with direct implications for […]
Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
arXiv:2605.14621v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) often hallucinate when language priors dominate weak or ambiguous visual evidence. Existing contrastive decoding methods mitigate this problem by comparing predictions from the original image with those from externally perturbed visual inputs, but such references can introduce off-manifold artifacts and require costly extra forward passes. We […]
Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
arXiv:2510.02837v2 Announce Type: replace Abstract: Although recent tool-augmented benchmarks involve complex requests, evaluation remains limited to answer matching, neglecting critical trajectory aspects like efficiency, hallucination, and adaptivity. The most straightforward method for evaluation is to compare an agent’s trajectory with the ground-truth, but annotating all valid ground-truth trajectories is prohibitively expensive. In this manner, we […]
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
arXiv:2605.11853v2 Announce Type: replace-cross Abstract: Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision. While finer-grained credit assignment is promising for effective policy updates, obtaining reliable local credit and assigning it to the right parts of the long-horizon trajectory remains […]