Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning

• URL: http://arxiv.org/abs/2607.00461v1
• Date: Wed, 01 Jul 2026 05:29:02 GMT
• Title: Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning
• Abstract summary: Continuous latent reasoning aims to discover implicit reasoning pathways that bridge the multimodal query and the final answer.<n>This introduces a severe train-inference mismatch: a training-time posterior, conditioned on the ground-truth answer, can exploit answer-dependent shortcuts.<n>Standard variational training then forces the inference-time prior to mimic a posterior that has access to information unavailable at test time, leading to poor performance.<n>We propose Asymmetric Mutual Variational Learning (AMVL), a framework that resolves this mismatch via a bidirectional calibration objective.
• Score: 31.446829707182445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuance. A promising alternative is continuous latent reasoning, where the goal is to discover implicit reasoning pathways that bridge the multimodal query and the final answer. However, this introduces a severe train-inference mismatch: a training-time posterior, conditioned on the ground-truth answer, can exploit answer-dependent shortcuts. Standard variational training then forces the inference-time prior to mimic a posterior that has access to information unavailable at test time, leading to poor performance. To address this, we propose Asymmetric Mutual Variational Learning (AMVL), a framework that resolves this mismatch via a bidirectional calibration objective. A forward KL divergence trains the target-agnostic prior to match the posterior, while a novel reverse KL divergence simultaneously regularizes the posterior, preventing it from collapsing into inference-incompatible regions and mitigating this ``answer leakage''. We provide theoretical analysis formalizing this leakage as prior contamination and prove that our dual-KL objective reduces it. We instantiate AMVL in a latent-integrated MLLM and show that it consistently outperforms strong discrete and latent-reasoning baselines, improving the average score on the complex BLINK benchmark by +10.83 and achieving gains of up to +32.00 on individual reasoning tasks, with analyses confirming improved latent-space stability.

Related papers

• RL Forgets! Towards Continual Policy Optimization [57.4336338996653]
  Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.<n>Recent work has increasingly favored reinforcement learning over supervised fine-tuning, driven by the belief that reinforcement learning is inherently less prone to forgetting.<n>We propose Continual Policy Optimization (CPO), a replay-free framework grounded in a prior-task behavioral KL objective.
  arXiv  Detail & Related papers  (2026-07-05T15:46:11Z)
• SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs [55.46289074417954]
  reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k.<n>We argue that a central structural constraint arises from reverse-KL regularization, which stabilizes training but inherently anchors the policy to the reference distribution.<n>We propose SAGE, a principled framework that enables controllable empirical support expansion by reshaping the reverse-KL anchor distribution itself.
  arXiv  Detail & Related papers  (2026-05-15T07:42:21Z)
• A Mutual Information Lower Bound for Multimodal Regression Active Learning [9.04041860173466]
  Mutual Information Lower Bound (MI-LB) is a closed-form approximation for Mixture Network ensembles.<n>We show that MI-LB matches or beats every baseline evaluated on benchmarks featuring multimodal systems.
  arXiv  Detail & Related papers  (2026-05-14T14:50:47Z)
• ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval [64.14282916266998]
  Composed Image Retrieval aims to retrieve target images based on a hybrid query comprising a reference image and a modification text.<n>We propose ReCALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline.<n>Experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-02T04:52:54Z)
• Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization [38.469173375694076]
  This paper systematically analyzes the root causes of hallucinations in Multimodal Large Language Models (MLLMs)<n>It identifies three critical factors: (1) an over-reliance on chained visual reasoning, where inaccurate initial descriptions anchor subsequent inferences to incorrect premises; (2) insufficient exploration diversity during policy optimization, leading the model to generate overly confident but erroneous outputs; and (3) destructive conflicts between training samples, where NTK similarity causes false associations and unstable parameter updates.<n> Experimental results demonstrate that our proposed method significantly reduces hallucination rates and effectively enhances the inference accuracy of MLLMs.
  arXiv  Detail & Related papers  (2026-01-09T07:59:18Z)
• Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity [13.211627219720796]
  Reinforcement Learning (RL) has become the de facto standard for tuning LLMs to solve tasks involving reasoning.<n>We argue that RL implicitly optimize the "mode-seeking" or "zero-forcing" Reverse KL to a target distribution causing the model to concentrate mass on certain high-probability regions of the target while others.<n>In this work, we instead begin from an explicit target distribution, obtained by filtering out incorrect answers while neglecting the relative probabilities of correct ones.
  arXiv  Detail & Related papers  (2025-12-05T18:56:40Z)
• In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning [51.56484100374058]
  We introduce a principled risk decomposition that separates the total ICL risk into two components: Bayes Gap and Posterior Variance.<n>For a uniform-attention Transformer, we derive a non-asymptotic upper bound on this gap, which explicitly clarifies the dependence on the number of pretraining prompts.<n>The Posterior Variance is a model-independent risk representing the intrinsic task uncertainty.
  arXiv  Detail & Related papers  (2025-10-13T03:42:31Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Probabilistic Variational Contrastive Learning [8.23660331371415]
  We propose a decoder-free framework that maximizes the evidence lower bound (ELBO)<n>We model the approximate posterior $q_theta(z|x)$ as a projected normal distribution, enabling the sampling of probabilistic embeddings.
  arXiv  Detail & Related papers  (2025-06-11T20:26:07Z)
• Hybrid Latent Reasoning via Reinforcement Learning [50.6763762323985]
  We explore latent reasoning by leveraging the capabilities of large language models (LLMs) via reinforcement learning (RL)<n>We introduce hybrid reasoning policy optimization (HRPO), an RL-based hybrid latent reasoning approach that integrates prior hidden states into sampled tokens with a learnable gating mechanism.<n>HRPO-trained LLMs remain interpretable and exhibit intriguing behaviors like cross-lingual patterns and shorter completion lengths.
  arXiv  Detail & Related papers  (2025-05-24T01:26:16Z)
• Improving Variational Autoencoders with Density Gap-based Regularization [16.770753948524167]
  Variational autoencoders (VAEs) are one of the powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. In practice, optimizing ELBo often leads the posterior distribution of all samples converge to the same degenerated local optimum, namely posterior collapse or KL vanishing. We introduce new training objectives to tackle both problems through a novel regularization based on the probabilistic density gap between the aggregated posterior distribution and the prior distribution.
  arXiv  Detail & Related papers  (2022-11-01T08:17:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.