arXiv:2607.15388v1 Announce Type: new Abstract: Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help…
arXiv:2605.15677v2 Announce Type: replace Abstract: Despite the rapid advancements in Vision-Language Models (VLMs), a critical gap remains in their ability to handle structured, controllable diagrammatic tasks…
arXiv:2603.01875v3 Announce Type: replace Abstract: Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles…
arXiv:2607.15374v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) ground whole objects well from free-form language queries, but they struggle when the query names a…
arXiv:2607.15898v1 Announce Type: cross Abstract: Current world models operate at a single level of abstraction, with most prioritizing perceptual fidelity while lacking the spatial reasoning and…
arXiv:2607.15456v1 Announce Type: new Abstract: Looped, weight-tied Transformers reduce parameters by reusing a block, but decoding still stores a separate K/V cache for every recurrence step.…
arXiv:2607.15485v1 Announce Type: cross Abstract: Score-based generative models exhibit a puzzling behavior: they often appear to cover all modes of a target multimodal distribution and yet…
arXiv:2607.15367v1 Announce Type: new Abstract: Desktop voice assistants are still dominated by cloud pipelines that ship raw audio off the machine and expose a fixed set…
arXiv:2607.09786v2 Announce Type: replace-cross Abstract: Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer. In our experiments, training with…
arXiv:2607.15856v1 Announce Type: new Abstract: Naturalistic language comprehension requires listeners to process both local probabilistic expectations and contextual semantic relations. Surprisal has been widely used to…
arXiv:2607.15331v1 Announce Type: new Abstract: Generalized few-shot 3D point-cloud segmentation (GFS-PCS) asks a model to segment a scene into many base classes seen at training time…
arXiv:2507.21018v2 Announce Type: replace-cross Abstract: Automated assessment of human motion plays a vital role in rehabilitation, enabling objective evaluation of patient performance and progress. Unlike general…
arXiv:2607.14345v2 Announce Type: replace Abstract: People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage:…
arXiv:2607.15530v1 Announce Type: cross Abstract: Binary Iterative Hard Thresholding (BIHT) is a simple, yet effective, greedy method for recovering a sparse vector from one-bit sign measurements.…
arXiv:2607.15314v1 Announce Type: new Abstract: Healthcare spans high-stakes communication, expert reasoning, and workflow execution, yet specialized LLMs that cover these use cases together remain limited. A…
arXiv:2602.01244v3 Announce Type: replace Abstract: Training agentic models for terminal-based tasks critically depends on high-quality terminal trajectories that capture realistic long-horizon interactions across diverse domains. However,…
arXiv:2605.04539v4 Announce Type: replace Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators…
arXiv:2602.05081v2 Announce Type: replace-cross Abstract: Gaussian-based representations have enabled efficient physically-based volume rendering at a fraction of the memory cost of regular, discrete, voxel-based distributions. However,…
arXiv:2605.20982v2 Announce Type: replace-cross Abstract: AlltoAll dispatch is the dominant bottleneck of MoE expert parallelism, and the interconnect community has responded with four families of mitigations:…
arXiv:2607.15457v1 Announce Type: new Abstract: We study robust peak-cost constrained reinforcement learning (RP-CRL), where the objective is to maximize expected reward while controlling the maximum cost…
arXiv:2607.15432v1 Announce Type: cross Abstract: Emergency department (ED) boarding occurs when admitted patients remain in the ED while awaiting inpatient beds. Boarding is a major driver…
arXiv:2607.11436v2 Announce Type: replace Abstract: Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable once it enters the language stack,…
arXiv:2607.15655v1 Announce Type: new Abstract: Masked diffusion language models (DLMs) enable parallel text generation by iteratively refining masked tokens, offering a promising alternative to autoregressive decoding.…
arXiv:2607.15861v1 Announce Type: new Abstract: Moderation systems increasingly rely on external toxicity tools, but those tools are unreliable under code-mixing, transliteration, slang, and language mismatch. We…