47 articles mentioning better-human-motion-h3-lora
arXiv:2610.24993v2 Announce Type: replace Abstract: The throughput gains of speculative decoding depend on the trade-off between acceptance length and execution latency. We ask when additional acceptance is worth the cost of obtaining it. We establish a comparison protocol spanning training, inferen
arXiv:2607.08409v2 Announce Type: replace-cross Abstract: LLM-based ASR adapted to regulated domains such as banking is bottlenecked by privacy: real speech is costly and legally constrained to collect, making synthetic text-to-speech (TTS) an attractive substitute. Yet synthetic speech stays acoust
arXiv:2610.25043v2 Announce Type: replace Abstract: Flow-matching vision-language-action (VLA) models generate an action chunk by iteratively denoising Gaussian noise, but typically execute only a short prefix before replanning with updated observations. Under this receding-horizon paradigm, the une
arXiv:2610.00661v3 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in parallel. Reinforcement learning with verifiable rewards (RLVR) reuses terminal feedback across thes
arXiv:2610.28192v1 Announce Type: cross Abstract: Token merging is an effective approach to reducing KV-cache memory consumption in autoregressive video generation by clustering temporally redundant tokens and retaining only a small set of representatives. Existing methods, however, typically apply
arXiv:2610.27488v1 Announce Type: new Abstract: Practitioner guidance holds that a large language model reviews a document better when the work is divided among agents. We test a narrow form of it in a controlled comparison of single-agent and multi-agent setups on a financial task, reviewing credit
arXiv:2609.04180v2 Announce Type: replace-cross Abstract: Gaps remain in our understanding of how large language models (LLMs) acquire knowledge during pre-training. We find that auxiliary views, conceptual reformulations, are key to this process. We design controlled experiments to isolate this. Fi
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Until recently, you could divide internet users into just two categories: bots and people. Websites have long allowed bots to perform automated tasks, like captur
arXiv:2505.10597v3 Announce Type: replace-cross Abstract: Reward models (RMs) are central to aligning large language models (LLMs) with human values, yet noisy preference feedback can induce reward misgeneralization through spurious correlations and overfitting. We characterize the training dynamics
arXiv:2610.22594v1 Announce Type: new Abstract: Medical multi-agent systems, in which LLM agents discuss a case, are increasingly studied for clinical decision support. Prompt injection, text that an attacker adds to a model's input, can manipulate LLMs into wrong decisions. How it affects these sys
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 LLM-assisted data curation creates a new operational tradeoff: higher-fidelity models and richer pr
arXiv:2604.03376v2 Announce Type: replace Abstract: Current work on radiology report evaluation has focused primarily on LLM-based metrics for chest X-rays (CXR), leaving open whether such approaches remain robust across other modalities and anatomies, and which model and prompt configurations are b
arXiv:2610.20682v1 Announce Type: cross Abstract: We introduce TurboMamba, a language-model architecture for faster inference, faster training, and better token prediction. A global Mamba-3 model runs once per completed token block. A small Transformer uses this global context and earlier tokens wit
Meta announced the Muse Spark Open AI model today, claiming that it's the "most capable US open-weight model to date." But the company also says that it's the "the first model in its class" that can "run on your desktop using two Apple M5 Ultra Mac Studios with the latest MLX framework." Meta and Ap
arXiv:2511.04473v4 Announce Type: replace-cross Abstract: Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While various solutions have been proposed, a comparison of methods is difficult due to the lack of challeng
arXiv:2610.17963v1 Announce Type: cross Abstract: Brick-and-mortar retailers face many different challenges that involve understanding thoroughly its products catalog and customer preferences. In particular, assortment optimization - proposing the ideal mix of products - and promotion planning hold
arXiv:2610.17696v1 Announce Type: cross Abstract: Identifying protein-ligand binding sites (pockets) is important for understanding protein function and developing drugs. However, no public method has leveraged co-folding models for novel pocket prediction; furthermore, this task lacks a suitable be
arXiv:2610.17948v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have attracted increasing research attention due to their bidirectional attention and arbitrary order decoding. However, there are two issues in dLLMs inference: the decoding difficulty is dominated by the toke
arXiv:2610.18108v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a scalable alternative when human evaluation is too costly. Unfortunately, LLM judgments can exhibit syst
arXiv:2610.19114v1 Announce Type: new Abstract: Activation steering controls large language models at inference time, but its effectiveness depends on the choice of reference data. We introduce genesis steering, which derives a genesis vector from contrastive examples in the model's own fine-tuning
arXiv:2610.20363v1 Announce Type: new Abstract: Neural operators learn mappings between function spaces, enabling fast surrogate solutions to partial differential equations. Despite remarkable architectural diversity, these methods often share a common input representation: raw coordinate-value pair
arXiv:2610.19789v1 Announce Type: new Abstract: Self-distillation in agentic reinforcement learning has produced a growing number of methods. However, existing evaluations often reuse published baseline scores under differing experimental conditions, provide few direct comparisons among contemporane
arXiv:2610.06269v2 Announce Type: replace Abstract: Open-ended scientific discovery often requires repeatedly proposing and evaluating candidate solutions. LLM-based systems can support this process by generating and refining executable solutions from verifier feedback. Methods such as TTT-Discover
arXiv:2605.26279v2 Announce Type: replace Abstract: Constraint Acquisition (CA) and related research on the validation and enhancement of Mathematical Programming (MP) models using domain knowledge artifacts are currently limited by inadequate benchmarks. The existing benchmarks are loosely organize
arXiv:2610.13092v1 Announce Type: new Abstract: AI agents depend on repeated decisions to accomplish tasks, with large language models (LLMs) commonly serving as their core decision makers. The recent emergence of Jev offers an opportunity to make these decisions faster and at lower cost. However, i
arXiv:2610.13476v1 Announce Type: new Abstract: Representational similarity measures (RSA, CKA, Procrustes) are chosen for the transformations they treat as irrelevant, and all of them take the set of conditions as given. That set is fixed by two decisions, which inputs are admitted and how they are
For six years, Danu founder Amy Ma has been working on a better way to sort recyclable waste.
arXiv:2610.11291v1 Announce Type: new Abstract: On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models. In this work, we ask a critical research question: Is on-policy sampling always beneficial for distilling arbitrary teacher-student pa
arXiv:2610.11206v1 Announce Type: new Abstract: Flat loss landscapes have long been linked to better generalization in neural networks. However, its role as a causal mechanism for generalization is less established. Grokking provides an unique testbed to understand this distinction: models are prone
arXiv:2610.02140v1 Announce Type: new Abstract: Introducing new capabilities to frontier models has long been the goal of posttraining, which predominantly employs supervised finetuning (SFT) and reinforcement learning (RL) to this end. Conventional wisdom dictates that RL enables strong generalizat
arXiv:2609.30036v4 Announce Type: replace Abstract: Latent world models plan toward goal images with a frozen pretrained predictor, without task rewards or extra trained heads. However, their planners struggle with long-range goals, and prior work addresses this by training extra components such as
arXiv:2609.39632v1 Announce Type: new Abstract: Test-time scaling improves language model reasoning by spending additional compute at inference. However, both classes of existing methods often fail to continue improving over long timescales. Parallel methods repeatedly sample independent answers fro
arXiv:2609.39901v1 Announce Type: new Abstract: Goal-conditioned reinforcement learning (GCRL) relies heavily on how target goals are represented to the policy. While recent methods encode goals via temporal distance, occupancy, or controllability, it remains unclear how much downstream performance
arXiv:2609.39687v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises student-sampled prefixes. Standard OPSD uses one fixed parameter setting at every state, but nearby setting
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 failures are the most informative negatives and that rejects must come from a model at least as large
arXiv:2609.28145v2 Announce Type: replace Abstract: Reinforcement learning (RL) improves reasoning, but its performance depends on the policy from which training begins. We study on-policy distillation (OPD) as a preparation stage for RL and ask whether its benefits extend beyond improvements in the
arXiv:2610.01026v1 Announce Type: cross Abstract: Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate specialized agents to work together on these tasks. Recent methods train LLMs to constru
arXiv:2609.40055v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides dense supervision directly on student-generated trajectories, making it an effective post-training strategy for vision-language models in temporal video grounding (TVG). However, existing pipelines typically cons
arXiv:2609.37304v1 Announce Type: cross Abstract: Large reasoning models improve performance on challenging problems by allocating additional computation before answering, but longer reasoning does not always lead to better results and can introduce substantial redundant reasoning on simple problems
arXiv:2609.36816v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a cornerstone for improving the reasoning capabilities of large language models (LLMs), but the need for on-policy data substantially limits training efficiency. Reusing off-policy data through importance sampling
arXiv:2602.02427v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved significant breakthroughs across various domains, but they can still produce unreliable or misleading outputs. For responsible LLM applications, uncertainty quantification techniques are used to estimate a
arXiv:2609.39958v1 Announce Type: new Abstract: Corporate and investment banking teams use presentations to support credit decisions and advise clients on financing and transactions. Producing these decks requires reconciling financial data, tracing sources and turning analysis into a recommendation
arXiv:2605.23448v2 Announce Type: replace-cross Abstract: This work examines an imbalance in artificial intelligence (AI) security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense ratio
arXiv:2609.37310v1 Announce Type: cross Abstract: With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Yet, recent progress in the field of LLM watermarking has increasingly been driven by improving details
arXiv:2609.38819v1 Announce Type: cross Abstract: Studying the alignment between the internal representations of vision models and the responses of the visual cortex to the same observed visual stimuli has enabled us to better understand human visual processing. However, studies so far have largely
arXiv:2609.36097v1 Announce Type: cross Abstract: Using predictive models to explain cognition requires more than accurate behavioral predictions. Input ablations offer an appealing route: remove information from a model and interpret the resulting performance change as evidence of its importance fo
arXiv:2609.36239v1 Announce Type: new Abstract: Large language models (LLMs) can predict human brain activity across a variety of brain regions during natural language comprehension. Typically, however, LLM-brain alignment is measured using one model for different regions of the brain, and then mode