$ALIGN alignment

Latest papers

1. Representation Conditioning for Generation cs.CV · 14 Oct · 2 hits

   Representation-alignment methods effectively accelerate the diffusion transformer training. REPA, for example, uses a…

2. Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance cs.RO · 14 Oct · 1 hit

   …To improve sample efficiency in data-expensive real-world settings, we propose Expert-Guided Value Alignment, which leverages sparse human interventions with under 20% training coverage to reshape the…

3. Manac\'a-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge cs.CL · 14 Oct · 3 hits

   …with statistical significance. We present Manac\'a-1B-Instruct-2, the second-generation post-training alignment of Manac\'a-1B (1.72B parameters, trained from scratch for PT-BR), with an SFT corpus of 291,223…

4. PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition cs.AI · 14 Oct · 2 hits

   …predict object coordinates, or utilize generative diffusion priors to synthesize composite images for visual alignment, both of which rely on static priors in digital spaces. However, these methods consistently…

5. Reliability-Aware Multimodal Sentiment Prediction Under Local Modality Missingness cs.CV · 14 Oct · 1 hit

   …faster than random positions (AUC gap 0.113 on validation). We also describe an auditable word-level alignment pipeline for raw clips; its outputs do not feed the predictive models.

6. ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models cs.CL · 14 Oct · 1 hit

   …of the observed change. Specifying the intended year in the prompt also offers little overall improvement in alignment with survey responses. These findings suggest that models often present a largely static picture of…

7. Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR cs.CL · 14 Oct · 1 hit

   …models (VLMs), charges a typo as much as a wrong name. We introduce semCER, which keeps CER's alignment and denominator and charges each grapheme edit a severity from an LLM judge, with no word…

8. ReAl: Refine neural operators via aligning dynamical flow cs.LG · 14 Oct · 2 hits

   …base prediction, recovering missing fine-scale structures while retaining the dominant dynamics. In the alignment stage, to mitigate the generative discrepancies amplified in the autoregressive rollout,…