ElasticFlow: One-Step Physics-Consistent Policy with Elastic Time Horizons for Language-Guided Manipulation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for embodied AI use iterative denoising to achieve high latency and lack physical consistency. |
| Approach: | They propose a distillation-free, physics-consistent one-step policy framework that reconstructs the Mean Field Theory by directly modeling the average velocity field. |
| Outcome: | Experiments on LIBERO, CALVIN, and RoboTwin show that the proposed framework outperforms state-of-the-art methods on long-horizon tasks. |
Similar Papers
From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons (2026.acl-long)
Copied to clipboard
| Challenge: | Autoregressive (AR) models rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregression models. |
| Approach: | They propose a framework that efficiently adapts autoregressive (AR) models to the diffusion paradigm. |
| Outcome: | The proposed framework reduces training costs by orders of magnitude while maintaining state-of-the-art performance. |
The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check (2026.acl-long)
Copied to clipboard
| Challenge: | Embodied and Tool-Calling agents are effective in planning and complex reasoning, but require causal, precise, and logically grounded reasoning mechanisms to be viable for agentic tasks. |
| Approach: | They propose a framework that integrates dLLMs as plug-and-play cognitive cores. |
| Outcome: | The proposed model breaks the sequential latency bottleneck in agentic interactions. |
SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have enabled dynamic reasoning in automated data analytics, but rigid, single-path workflows restrict strategic exploration and often lead to suboptimal outcomes. |
| Approach: | a new framework replaces rigid workflows with adaptive, multi-path planning . the framework offers two operating modes: SPIO-S and SPIO -E . |
| Outcome: | a new framework outperforms state-of-the-art pipelines on Kaggle and OpenML benchmarks. |
On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration (2026.findings-acl)
Copied to clipboard
Huaisheng Zhu, MingYu Liu, Junze Liu, Zhen Ge, Tian Wang, Jiri Gesi, Dakuo Wang, Weiqi Zhang, Houyu Zhang, Yufan Guo, Xian Li, Bing Yin, Sujay Sanghavi
| Challenge: | Recent studies have demonstrated that masked diffusion models (MDMs) can surpass autoregressive models (ARMs) in various tasks. |
| Approach: | They propose a method to calibrate early token predictions without demonstration data by distilling an unnormalized target distribution into the original model. |
| Outcome: | Experiments on math, planning, and RLHF tasks show that COPSD improves both effectiveness and efficiency, and further enhances performance when combined with supervised fine-tuning. |
đťś™-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing inference-time optimization strategies address the shortsightedness of auto-regressive generation, but the vast search space leads to excessive exploration and insufficient exploitation. |
| Approach: | They propose a decoding strategy that approximates two distributions via foresight and clustering to provide an efficient estimation of step value. |
| Outcome: | The proposed decoding strategy outperforms strong baselines in performance and efficiency. |
To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing tools that integrate chain-of-thought reasoning and code execution lack metacognitive awareness to integrate tools. |
| Approach: | They propose a framework that synergizes structured exploration with off-policy RL optimization to create a cycle between metacognitive tool-use decisions and evolving capabilities. |
| Outcome: | The proposed framework improves over 11% on MATH500 and 9.4% on AIME without o1-like CoT. |
NITI: Neural Plan Concretization for Incremental Execution, Bridging and Trigger Inference from Underspecified Human Policies (2026.findings-acl)
Copied to clipboard
| Challenge: | Using NITI, we examine the performance of a safety-critical automated insulin dosing task with minimal contextualization infence overhead. |
| Approach: | They propose a framework that treats large language models as execution-time concretizers of human intent that incrementally executes abstract policies via verifier-grounded interfaces. |
| Outcome: | The proposed framework outperforms one-shot and chain-of-thought baselines on two structurally distinct embodied domains: a world cubing championship 22 Rubik’s Cube scramble and a safety-critical automated insulin dosing task. |
DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding (2026.findings-acl)
Copied to clipboard
| Challenge: | Autoregressive (AR) decoding in large language models is latency-bounded by strictly sequential token generation. |
| Approach: | They propose a diffusion-based drafter that proposes multi-token candidates and then verifies them in parallel by the target model. |
| Outcome: | The proposed drafter generates multi-token proposals in a single forward pass while remaining compatible with standard AR verifiers. |
FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing models that correct errors in the model but lack a high quality of output . a novel training framework that matches inference noise to the model's inference signal improves performance . |
| Approach: | They propose a training framework that matches inference noise to model errors by perturbing the self-conditioning signal to match inference errors. |
| Outcome: | The proposed framework surpasses standard continuous diffusion models while providing 400x faster inference speed. |
DecoCal: Decoding with Calibration in Diffusion Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion Large Language Models (DLLMs) generate text via iterative token denoising . but decoding is challenging, with many tokens appearing predictable early . |
| Approach: | They propose a Decoding framework that performs Calibration of token-level confidence across diffusion steps and leverages the calibrated results to guide decoding decisions. |
| Outcome: | Experiments on multiple DLLMs and benchmarks show that DecoCal improves generation accuracy compared to existing strategies. |