Knowledge catalogue
arXiv:2609.34284v2 Announce Type: replace Abstract: Personalized LLMs must decide, for each stored preference, whether the current context calls for applying or suppressing it, which we call its appli
arXiv:2609.39970v1 Announce Type: new Abstract: Robot brain models integrate vision, language, and robot state to generate actions for complex manipulation tasks. Most predict fixed-length action chun
arXiv:2609.38824v1 Announce Type: new Abstract: Human-aware exoskeleton walking requires reconstructing gait, tracking diverse motions under dynamic constraints, and preserving human timing. We presen
arXiv:2609.38427v1 Announce Type: cross Abstract: Major venues now publish detailed rules about how authors, reviewers, and area chairs may use AI, and those rules differ by role, by task, and by what
arXiv:2609.40147v1 Announce Type: new Abstract: We establish an exponential iteration lower bound in the number of states for Howard's policy iteration on deterministic discounted Markov decision proc
arXiv:2609.39637v1 Announce Type: new Abstract: A central question in deploying teams of mobile robots for persistent monitoring is how task performance scales with fleet size, and whether this scalin
arXiv:2609.40165v1 Announce Type: cross Abstract: We present PrefPI (Preference-Guided Policy Iteration), an iterative framework for steering pretrained generative robot policies using only relative p
arXiv:2603.24528v2 Announce Type: replace Abstract: Vision-language models like CLIP are trained with the objective of aligning text and image pairs. Beyond text prompts alone, recent works show that
arXiv:2609.38925v1 Announce Type: new Abstract: Multimodal federated learning (MFL) has emerged as a pivotal paradigm for leveraging distributed data to enhance model performance. However, existing me
arXiv:2609.40131v1 Announce Type: cross Abstract: Rank-constrained tensor neural networks reduce the parameterization of high-order inputs, but they do not explicitly constrain class geometry in the l
arXiv:2609.40051v1 Announce Type: cross Abstract: Estimating causal effects from observational data is central to science and policy, but the effects are not identified when confounders are unmeasured
arXiv:2609.38795v1 Announce Type: new Abstract: Block drafters for speculative decoding are commonly trained on corpora written by external models, where a single off-policy token invalidates supervis
arXiv:2512.22802v2 Announce Type: replace-cross Abstract: Step distillation accelerates diffusion sampling by training a few-step student to imitate a many-step teacher, but distillation itself remain
arXiv:2609.38680v1 Announce Type: cross Abstract: Text-to-image diffusion models are personalized to a subject by DreamBooth fine-tuning on a handful of its images. Increasingly, these images come fro
arXiv:2609.38598v1 Announce Type: new Abstract: Partially observable environments pose a fundamental challenge in deep reinforcement learning, requiring agents to compress temporal information from ob
arXiv:2609.39106v1 Announce Type: new Abstract: Conservative bandits must improve an incumbent policy without exhausting a prescribed performance budget. When the incumbent is uncertain, separately bo
arXiv:2609.39275v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own generated prefixes with token-level teacher feedback, but transmitting or storing the teacher's
arXiv:2609.39757v1 Announce Type: cross Abstract: Black-box distillation is a practical route for transferring capabilities from API-accessible large language models that expose only text outputs into
arXiv:2609.38526v1 Announce Type: cross Abstract: Scaling laws for optimization against reward models in AI alignment have pinned down how performance depends on optimization effort---measured by a KL
arXiv:2609.39245v1 Announce Type: new Abstract: In interactive scenarios, an autonomous driving system is required to generate ego actions under the influence of other agents' behaviors. Existing Worl
arXiv:2609.38914v1 Announce Type: new Abstract: Evaluating interactive agents is expensive. Agent behavior is stochastic, so reliability must be measured over repeated trials, but failures are rare an
The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards the successful ones. This becomes problematic in th
arXiv:2609.39685v1 Announce Type: cross Abstract: Long-horizon robot manipulation reuses skills across many task compositions, but improving these compositions with additional end-to-end demonstration
arXiv:2609.40149v1 Announce Type: new Abstract: Policy regularization in offline reinforcement learning balances policy improvement against reliance on uncertain value estimates. This balance can diff
arXiv:2609.40360v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet their predictions r
arXiv:2609.39892v1 Announce Type: new Abstract: Looped Transformers repeatedly apply the same set of Transformer layers, giving them a recurrent architecture for latent computation. Their strong perfo
arXiv:2609.38987v1 Announce Type: new Abstract: Preference distillation typically treats a teacher response as preferred and the student's own response as rejected. This assumes that self-generated fa
arXiv:2609.38717v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) commonly perform spatial reasoning through chain-of-thought (CoT), encoding intermediate reasoning as autoregress
arXiv:2609.38712v1 Announce Type: new Abstract: Long-horizon agentic workflows require models to sustain repeated state-dependent actions all while the context grows, sub-task complexity changes, and
arXiv:2609.39091v1 Announce Type: cross Abstract: Inference-time alignment of flow and diffusion-based models is critical for achieving flexible generative modeling. Theoretically, Doob's h-transform
arXiv:2609.39807v1 Announce Type: cross Abstract: Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest. However, role-play complicate
arXiv:2609.38325v1 Announce Type: new Abstract: We introduce modal kinetic typography, which animates a vector glyph to express a semantic concept while keeping it legible. Our key idea is to build mo
arXiv:2609.38653v1 Announce Type: cross Abstract: Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated agents to reproduce increasingly complex human mot
arXiv:2609.39599v1 Announce Type: cross Abstract: 3D visuomotor policies provide a strong foundation for spatially precise manipulation, yet current text-to-3D policies struggle to follow unseen fine-
arXiv:2609.39055v1 Announce Type: new Abstract: How can we personalize a shared expert library from a user's pairwise choices? Prior work can realize different reward trade-offs by merging reward-spec
arXiv:2609.39235v1 Announce Type: cross Abstract: World models offer a promising way to help robots understand how the physical world evolves and plan complex behaviours through imagination. Yet exist
arXiv:2609.39797v1 Announce Type: new Abstract: Autonomous powder weighing is one of many bottlenecks in laboratory automation due to the complex, non-linear dynamics of heterogeneous materials. Robot
arXiv:2609.39397v1 Announce Type: cross Abstract: We study data-driven multi-period lost-sales inventory control under censored demand, where a stockout reveals only that demand exceeded the stocking
arXiv:2609.38547v1 Announce Type: cross Abstract: Defining a weighted mean over probability measures under probability metrics is a central tool in probabilistic machine learning. Under the Wasserstei
arXiv:2609.39162v1 Announce Type: cross Abstract: Speaker diarization systems based on speaker embeddings and neural diarization exploit complementary forms of speaker information, but their intermedi
arXiv:2609.38666v1 Announce Type: cross Abstract: On-policy distillation (OPD) learns from teacher feedback on student-generated responses and has shown promise in reducing forgetting relative to supe
arXiv:2609.38683v1 Announce Type: cross Abstract: Cinematic camera motion is a fundamental storytelling tool, defined not only by where the camera is positioned in the scene, but also by how it moves
arXiv:2609.38889v1 Announce Type: new Abstract: Constrained multi-agent control requires more than predicting rewarding actions: an action can cease to be executable as contact windows, shared capacit
arXiv:2609.39531v1 Announce Type: cross Abstract: We study the problem of estimating the guidance that steers the distribution learned by a diffusion generative model toward a tilted target q_0 propto
arXiv:2609.38494v1 Announce Type: cross Abstract: Robotic manipulation integrates vision, touch, and language, whose importance shifts across stages: vision guides reaching, while touch, through its e
arXiv:2609.38995v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a student on its own generated responses using feedback from the same model conditioned on privileged informat
arXiv:2609.39971v1 Announce Type: cross Abstract: Vision-language-action (VLA) models can exceed 90% success on in-distribution tasks and withstand nuisance changes that preserve the required action,
arXiv:2609.38964v1 Announce Type: new Abstract: Multi-agent debate (MAD) is often used to improve large language model (LLM) reasoning, but sequential debate is rarely a neutral aggregator of agents'
arXiv:2609.38818v1 Announce Type: new Abstract: Organizations increasingly route employee feedback to leaders through large language model (LLM) summaries, an unaudited layer that silences already-spo
arXiv:2609.38927v1 Announce Type: cross Abstract: World models aim to learn representations of real-world environments and predict their future evolution. Recent object-centric world models have made
arXiv:2609.39640v1 Announce Type: cross Abstract: Cross-lingual transfer describes how knowledge in a source language benefits a target language. Measuring it quantitatively requires broad multilingua
arXiv:2609.37061v1 Announce Type: cross Abstract: We view fairness as a property of distributional stability. Rather than assessing a predictor under a fixed data distribution, we study how its predic
arXiv:2609.38161v1 Announce Type: new Abstract: Evaluations of graph reconstruction by language models typically report a single aggregate distance between the original and the reconstructed graph. We
arXiv:2609.36058v1 Announce Type: new Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) has highlighted the effectiveness of simple critic-free policy-gradient methods
arXiv:2609.38132v1 Announce Type: new Abstract: We study average-reward weakly-coupled Markov decision processes (WCMDPs), where a WCMDP consists of N smaller MDPs, called arms, that share multiple pe
arXiv:2609.36250v1 Announce Type: cross Abstract: Action chunking provides temporal abstraction in reinforcement learning by selecting short action sequences instead of individual actions, but many ex
arXiv:2609.32472v2 Announce Type: replace Abstract: Document rerankers determine what evidence reaches the downstream model in RAG and deep research, yet mainstream rerankers select by relevance match
arXiv:2609.38170v1 Announce Type: new Abstract: Pixel diffusion models generate RGB images directly, avoiding the bottleneck of an autoencoder, yet their outputs still systematically underrepresent fi
arXiv:2609.36993v1 Announce Type: new Abstract: Complex tasks for underwater robots remain limited by the capabilities of their controllers. Learning a better one for a soft, underactuated robotic fis
arXiv:2603.12717v2 Announce Type: replace-cross Abstract: Vision-language-action policies map camera images and natural-language instructions to a robot's motor actions. Some of these policies are des