Knowledge catalogue
arXiv:2610.20687v1 Announce Type: new Abstract: Residual context is key to unlocking the speed-quality Pareto frontier of diffusion language models (DLMs) by carrying forward predictive distributions
arXiv:2610.20993v1 Announce Type: new Abstract: Reordering multiple-choice options can change a model's answer, an effect studied as selection bias (a preference for certain option letters) and as ord
arXiv:2610.21345v1 Announce Type: new Abstract: Agentic knowledge graph question answering(KGQA) relies on sequences of executable operations, but trajectory-level rewards obscure their individual con
arXiv:2602.18891v2 Announce Type: replace-cross Abstract: Advances in large language models (LLMs) are rapidly transforming scientific work, yet empirical evidence on how these systems reshape researc
arXiv:2610.21434v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies generate action sequences that reduce repeated inference, but deciding how much of each sequence to execute is c
Presenting the Generative AI Fizzle™ ANTHROPIC’S IPO VALUATION EXPECTATIONS DROP FROM 2 TRILLION TO 1.5 TRILLION Some investors are considering a 1.5 trillion valuation for Anthropic’s upcoming IPO, d
arXiv:2610.21088v1 Announce Type: new Abstract: Test-time search can improve agent performance by exploring alternative actions and using a critic to select promising branches. We study this approach
arXiv:2610.20852v1 Announce Type: cross Abstract: Negation is a fundamental aspect of language understanding and it is important vision-language models (VLMs) are able to process it effectively. We in
arXiv:2610.22056v1 Announce Type: new Abstract: Traditional reinforcement learning (RL) algorithms face significant limitations in handling long-term tasks with sparse rewards. Recent advancements hav
arXiv:2610.21764v1 Announce Type: new Abstract: A fixed discount factor in Q-learning imposes a single planning horizon throughout training, despite the differing demands of early exploration and long
arXiv:2610.22238v1 Announce Type: new Abstract: Masked diffusion models (MDMs) accelerate generation by unmasking multiple tokens in parallel, but sampling these tokens independently ignores their cor
arXiv:2610.20947v1 Announce Type: cross Abstract: Deep learning models, particularly Long Short-Term Memory networks, are increasingly used for operational streamflow forecasting, with ensemble spread
arXiv:2607.18915v2 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), modern systems not only possess strong foundational capabilities and extensive knowledge
arXiv:2610.21640v1 Announce Type: new Abstract: Reinforcement learning (RL) has been a critical paradigm for improving large language model (LLM) reasoning and agentic capabilities, but its efficiency
arXiv:2610.22178v1 Announce Type: cross Abstract: We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data that sets a new Pareto frontier between performance
arXiv:2610.21550v1 Announce Type: new Abstract: We study Text-and-Image-to-Image (TI2I) flow matching methods for controllable image editing. In a broader generative modeling context, Classifier-Free
arXiv:2610.22336v1 Announce Type: new Abstract: We develop a robust reinforcement learning (RL) framework for learning adaptive treatment policies that generalize across patients and remain reliable u
arXiv:2610.21682v1 Announce Type: cross Abstract: Reinforcement learning (RL) can become off-policy due to training-inference mismatch, mini-batch updates, and asynchronous training.The resulting mism
arXiv:2610.22282v1 Announce Type: new Abstract: Reinforcement learning can align visual generators with reward signals beyond their pretraining objectives, but existing score-function methods typicall
arXiv:2512.15756v2 Announce Type: replace-cross Abstract: Human-imposed design conventions can restrict the alternatives represented in scientific training data and shape the search preferences learne
arXiv:2610.21061v1 Announce Type: cross Abstract: Discrete diffusion models have become a powerful framework for modeling complex discrete distributions across a range of applications. While theoretic
arXiv:2610.20773v1 Announce Type: new Abstract: Calibrating a conformal prediction set at each early exit does not preserve coverage once a data-dependent exit is selected. We construct one terminal p
arXiv:2610.20766v1 Announce Type: new Abstract: Imagined speech decoding from EEG offers a promising route toward naturalistic brain-computer interfaces. Traditional closed-set classifiers treat seman
arXiv:2610.21695v1 Announce Type: new Abstract: Fixed-function CNN accelerators make edge inference fast and energy-efficient, but they execute only networks that obey a precise numerical contract. On
arXiv:2610.22217v1 Announce Type: cross Abstract: Reinforcement learning (RL) can elicit specialized visual capabilities in vision-language models (VLMs), yet jointly optimizing heterogeneous objectiv
arXiv:2610.20968v1 Announce Type: cross Abstract: Executing heavy-duty physical manipulation in unpredictable environments remains a major challenge for quadrupedal robots lacking dedicated manipulato
arXiv:2606.14535v2 Announce Type: replace Abstract: Recent visual imitation learning systems have widely adopted multi-camera setups with wrist-mounted cameras as the de facto standard. However, manip
arXiv:2610.22152v1 Announce Type: cross Abstract: Reinforcement learning agents optimize exactly the reward signal they are given, which can diverge sharply from an intended true objective when that s
arXiv:2610.21114v1 Announce Type: cross Abstract: Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores. The
arXiv:2603.14645v2 Announce Type: replace Abstract: In this paper, we study the diffusability (learnability) of variational autoencoders (VAEs) in latent diffusion. We first derive distribution-free b
arXiv:2610.21638v1 Announce Type: cross Abstract: Vision Transformers deployed in medical imaging exploit spurious correlations, yet the internal mechanisms remain unidentified and impossible to fix.
arXiv:2610.20894v1 Announce Type: cross Abstract: This paper investigates the statistical behavior of Stochastic Gradient Descent (SGD) with constant step size under the framework of iterated random f
arXiv:2610.21156v1 Announce Type: new Abstract: Proactive dialogue agents must guide multi-turn interactions toward task goals while adapting to users whose intentions and attitudes evolve. Existing p
arXiv:2610.22352v1 Announce Type: new Abstract: Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the visual details of a reference image.
arXiv:2610.22192v1 Announce Type: new Abstract: Converting verifier outcomes into useful policy updates and partial progress into complete task resolution is crucial for terminal agents. We present Te
arXiv:2610.21748v1 Announce Type: new Abstract: Spiking neural networks (SNNs) offer a compelling pathway toward energy-efficient artificial intelligence, fundamentally anchored in presynaptic input-d
arXiv:2610.21919v1 Announce Type: new Abstract: Active Feature Acquisition (AFA) sequentially selects features to maximize predictive accuracy under an acquisition budget. A natural heuristic greedily
arXiv:2509.26226v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long context lengths during traini
arXiv:2602.23959v2 Announce Type: replace Abstract: Recent MLLMs increasingly rely on visual chain-of-thought to perform region-grounded reasoning over images. However, existing approaches ground regi
arXiv:2610.21974v1 Announce Type: cross Abstract: Deepfake detectors safeguard against misinformation, rendering their failures as much a societal as a technical concern. As generators constantly evol
arXiv:2610.21978v1 Announce Type: new Abstract: Biological visual navigation achieves remarkable robustness at extremely low power, whereas frame-based robotic systems relying on artificial neural net
arXiv:2610.05373v2 Announce Type: replace Abstract: On-policy distillation (OPD) has emerged as an effective post-training paradigm for language models, with recent efforts extending it to block diffu
arXiv:2610.21515v1 Announce Type: new Abstract: Language-conditioned humanoid motion generation enables users to create and refine robot movements through natural language. The central challenge is to
arXiv:2610.22236v1 Announce Type: cross Abstract: On-policy distillation consolidates specialist models into one student at the price of rollouts, teacher passes and gradient steps for every teacher.
arXiv:2610.21582v1 Announce Type: new Abstract: Transfer learning in stochastic multi-armed bandits is typically studied assuming that prior data forms a fixed offline dataset or is generated by a kno
arXiv:2610.21922v1 Announce Type: new Abstract: Many vision-language-action policies rely on action-labeled robot demonstrations and lack an explicit mechanism for predicting future visual states. The
arXiv:2610.22327v1 Announce Type: cross Abstract: Time Series Language Models (TSLMs) enable language-based understanding and reasoning over temporal data, yet a fundamental question remains: what inf
arXiv:2509.24072v5 Announce Type: replace-cross Abstract: Large vision-language models (LVLMs) perform well on multimodal tasks, but their ability to reason and precisely align visual and textual info
arXiv:2610.21735v1 Announce Type: new Abstract: Object manipulation often requires combining non-prehensile actions with grasping. However, existing approaches typically develop these capabilities sep
arXiv:2610.22368v1 Announce Type: new Abstract: Real-world post-training of generalist robot policies faces two challenges: partial observability makes action selection ambiguous, while offline post-t
arXiv:2610.20669v1 Announce Type: new Abstract: Reward-guided discrete diffusion enables test-time alignment with downstream objectives, but applying Sequential Monte Carlo (SMC) guidance at every den
arXiv:2610.22311v1 Announce Type: new Abstract: Video world models turn actions and camera motion into long visual rollouts, making video a natural interface for interactive simulation. Such interacti
arXiv:2610.21985v1 Announce Type: new Abstract: Flow-based Vision-Language-Action (VLA) policies are inherently stochastic: different noise seeds can produce action chunks of varying quality from the
arXiv:2610.21601v1 Announce Type: cross Abstract: Policy-shift distillation reuses the difference between a teacher's log probabilities before and after reinforcement learning (RL) as supervision on s
arXiv:2610.21915v1 Announce Type: new Abstract: Vision-language-action (VLA) policies are typically trained with action prediction as the primary supervision signal, since robots ultimately execute ac
arXiv:2610.21139v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used upstream of decision-making to clean data, detect label errors, and reconstruct missing values. Yet
arXiv:2610.21160v1 Announce Type: new Abstract: Dual-system vision-language-action (VLA) models pair a high-frequency fast policy with a slow, expensive module, and published trigger mechanisms for in
arXiv:2610.21422v1 Announce Type: cross Abstract: Understanding video content requires reasoning at multiple levels of granularity, from identifying objects to interpreting their interactions and loca
arXiv:2604.03867v2 Announce Type: replace Abstract: Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulati
arXiv:2610.22184v1 Announce Type: cross Abstract: Current humanoid dexterous manipulation remains largely confined to end-effectors and simple grasps, falling short of humans' ability to engage the en