Tianyu Zhang

GCAM-Gym: A Benchmark for Agent-Based Climate Policy Search

Zhenghan Tai

Xinyu Wang

Irina Rish

Comparing climate-policy search methods requires accounting for differences in policy control, available observations, feedback timing, and … (voir plus)simulator budgets. We introduce GCAM-Gym, a Gymnasium-compatible environment that supports full-policy evaluation and stepwise control through a common interface and exposes the components of the policy objective. We compare seven search and control systems in three settings: target attainment and cost, cost-temperature trade-offs, and one-step delayed feedback. Each system is evaluated with ten seeds per setting, for a total of 3,210 attempted GCAM evaluations. Four systems share a budget of 24 attempts per seed; among these, CMA-ES achieves the highest interquartile mean (IQM) of the best returns from completed policy evaluations in all three settings. We release the evaluation archive and analysis tools to reconstruct the reported comparisons without running GCAM.

2026-10-15

arXiv (prépublication)

When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks

C.-T.D. Lo

Lu Li

Diji Yang

Yunkai Zhang

Yi Zhang

Chung-Hsiang Lo

In the LLM era, many symbolic and structured problems are presented to models through 1D text serialization. Yet some such problems are nati… (voir plus)vely two-dimensional: their relevant relations, such as row--column correspondence or spatial adjacency, are defined by position in a 2D layout rather than by sequential order. This raises a representational question: does preserving the same symbolic entries in a 1D sequence also preserve the relational structure needed for computation? We study this issue through the lens of serialization friction: the representational mismatch in which the same underlying task instances and entries are still present, but relations that depend on layout become implicit under 1D serialization. The study uses a controlled synthetic testbed of three tasks: matrix transpose, Conway's Game of Life, and LU decomposition. In each task, the same instances are presented either as 1D text serialization or as their native 2D layout rendered as an image. Across this testbed, 1D serialization degrades more sharply as task size grows, and errors under serialization exhibit spatially structured patterns, suggesting that this presentation choice is consequential within our testbed. To further interpret these results, we add supplementary analyses that include a within-visual probe and an additional comparison of the two input presentations under the mixed-training transpose setting. These findings suggest that, for layout-defined tasks, reducing inputs to 1D serialization is not a neutral choice of representation.

2026-04-28

arXiv (prépublication)

SCOPE: Selective Cross-modal Orchestration of Visual Perception Experts

Suyuchen Wang

Chao Wang

Juan A. Rodriguez

Ahmed Masry

Xiangru Jian

Perouz Taslakian

Vision-language models (VLMs) benefit from multiple vision encoders, but naively stacking them yields diminishing returns while multiplying … (voir plus)inference costs. We propose SCOPE, a Mixture-of-Encoders (MoEnc) framework that dynamically selects one specialized encoder per image-text pair via instance-level routing, unlike token-level routing in traditional MoE. SCOPE maintains a shared encoder and a pool of routed encoders. A lightweight router uses cross-attention between text prompts and shared visual features to select the optimal encoder from the routed encoders. To train this router, we introduce dual entropy regularization with auxiliary losses to balance dataset-level load distribution with instance-level routing confidence. Remarkably, SCOPE with one shared plus one routed encoder outperforms models using all four extra encoders simultaneously, while reducing compute by 24-49%. This demonstrates that intelligent encoder selection beats brute-force aggregation, challenging the prevailing paradigm in multi-encoder VLMs.

2026-03-01

MM_Intelligence @ International Conference on Learning Representations (poster)

The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning

Donghang Wu

Yuxin Li

Hexin Liu

Chen Chen

Eng Siong Chng

During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal… (voir plus) cognitive processing may not always manifest as explicit linguistic structures, it is instrumental in formulating high-quality responses. Inspired by this cognitive phenomenon, we propose a novel **F**ull-duplex **LA**tent and **I**nternal **R**easoning method named FLAIR that conducts *latent* thinking simultaneously with speech perception. Unlike conventional "thinking" mechanisms in NLP, which require post-hoc generation, our approach aligns seamlessly with spoken dialogue systems: during the user’s speaking phase, it recursively feeds the latent embedding output from the previous step into the next step, enabling continuous reasoning that strictly adheres to causality without introducing additional latency. To enable this latent reasoning, we design an Evidence Lower Bound-based objective that supports efficient supervised finetuning via teacher forcing, circumventing the need for explicit reasoning annotations. Experiments demonstrate the effectiveness of this think-while-listening design, which achieves competitive results on a range of speech benchmarks. Furthermore, FLAIR robustly handles conversational dynamics and attains competitive performance on full-duplex interaction metrics.

2025-12-31

International Conference on Machine Learning (Accept (regular))

On The Surprising Effectiveness of a Single Global Merging in Decentralized Learning

Tongtian Zhu

Mingze Wang

Zhanpeng Zhou

Can Wang

Decentralized learning provides a scalable alternative to parameter-server-based training, yet its performance is often hindered by limited … (voir plus)peer-to-peer communication. In this paper, we study how communication should be scheduled over time to improve global generalization, including determining when and how frequently devices synchronize. Counterintuitive empirical results show that concentrating communication budgets in the later stages of decentralized training remarkably improves global generalization. Surprisingly, we uncover that fully connected communication at the final step, implemented by a single global merging, can significant improve the generalization performance of decentralized learning under serve high data heterogeneity. Our theoretical contributions, which explains these phenomena, are first to establish that the globally merged model of decentralized SGD can match the convergence rate of parallel SGD. Technically, we reinterpret part of the discrepancy among local models, which were previously considered as detrimental noise, as constructive components essential for matching this rate. This work provides promising results that decentralized learning is able to generalize under high data heterogeneity and limited communication, while offering broad new avenues for model merging research. The code will be made publicly available.

2025-12-31

International Conference on Learning Representations (Accept (Oral))

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

Juan A. Rodriguez

Chao Wang

Akshay Kalkunte Suresh

Abhay Puri

Xiangru Jian

Pierre-Andre Noel

Sathwik Tejaswi Madhusudhan

Enamul Hoque

Christopher Pal

Issam H. Laradji

David Vázquez

Perouz Taslakian … (voir 2 de plus)

Spandana Gella

Sai Rajeswar

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges… (voir plus) on having a good connector that maps visual features generated by a vision encoder to a shared embedding space with the LLM while preserving semantic similarity. Existing connectors, such as multilayer perceptrons (MLPs), lack inductive bias to constrain visual features within the linguistic structure of the LLM's embedding space, making them data-hungry and prone to cross-modal misalignment. In this work, we propose a novel vision-text alignment method, AlignVLM, that maps visual features to a weighted average of LLM text embeddings. Our approach leverages the linguistic priors encoded by the LLM to ensure that visual features are mapped to regions of the space that the LLM can effectively interpret. AlignVLM is particularly effective for document understanding tasks, where visual and textual modalities are highly correlated. Our extensive experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods, with larger gains on document understanding tasks and under low-resource setups. We provide further analysis demonstrating its efficiency and robustness to noise.

2025-12-02

Conference on Neural Information Processing Systems (Accept (poster))

Majority of the Bests: Improving Best-of-N via Bootstrapping

Amin Rakhsha

Kanika Madan

Amir-massoud Farahmand

Amir Khasahmadi

Sampling multiple outputs from a Large Language Model (LLM) and selecting the most frequent (Self-consistency) or highest-scoring (Best-of-N… (voir plus)) candidate is a popular approach to achieve higher accuracy in tasks with discrete final answers. Best-of-N (BoN) selects the output with the highest reward, and with perfect rewards, it often achieves near-perfect accuracy. With imperfect rewards from reward models, however, BoN fails to reliably find the correct answer and its performance degrades drastically. We consider the distribution of BoN's outputs and highlight that, although the correct answer does not usually have a probability close to one under imperfect rewards, it is often the most likely outcome. This suggests that the mode of this distribution can be more reliably correct than a sample from it. Based on this idea, we propose Majority-of-the-Bests (MoB), a novel selection mechanism that estimates the output distribution of BoN via bootstrapping and selects its mode. Experimental results across five benchmarks, three different base LLMs, and two reward models demonstrate consistent improvements over BoN in 25 out of 30 setups. We also provide theoretical results for the consistency of the bootstrapping. MoB serves as a simple, yet strong alternative to BoN and self-consistency, and more broadly, motivates further research in more nuanced selection mechanisms.

2025-12-02

Conference on Neural Information Processing Systems (Accept (poster))

Scaling Latent Reasoning via Looped Language Models

Ruiming Zhu

Zixuan Wang

Kai Hua

Ziniu Li

Haoran Que

Boyi Wei

Zixin Wen

Fan Yin

He Xing

Li Li

Jiajun Shi

Kaijing Ma

Shanda Li

Taylor Kergan

Andrew C. Smith

Xin Qu

Mude Hui

Bohong Wu

Qiyang Min … (voir 13 de plus)

Hongzhi Huang

Xun Zhou

Wei Ye

Jiaheng Liu

Jian Yang 0030

Yunfeng Shi

Chenghua Lin

Enduo Zhao

Tianle Cai

Ge Zhang

Wenhao Huang

Jason K. Eshraghian

Modern LLMs are trained to"think"primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-trai… (voir plus)ning and under-leverages pre-training data. We present and open-source Ouro, named after the recursive Ouroboros, a family of pre-trained Looped Language Models (LoopLM) that instead build reasoning into the pre-training phase through (i) iterative computation in latent space, (ii) an entropy-regularized objective for learned depth allocation, and (iii) scaling to 7.7T tokens. Ouro 1.4B and 2.6B models enjoy superior performance that match the results of up to 12B SOTA LLMs across a wide range of benchmarks. Through controlled experiments, we show this advantage stems not from increased knowledge capacity, but from superior knowledge manipulation capabilities. We also show that LoopLM yields reasoning traces more aligned with final outputs than explicit CoT. We hope our results show the potential of LoopLM as a novel scaling direction in the reasoning era. Our model is available here: http://ouro-llm.github.io.

2025-10-28

ArXiv (prépublication)

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping

Christopher Pal

2025-10-02

ArXiv (prépublication)

Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning

Marco Jiralerspong

Esther Derman

Danilo Vucetic

Nikolay Malkin

Bilun Sun

Pierre-Luc Bacon

Gauthier Gidel

A major bottleneck in scientific discovery consists of narrowing an exponentially large set of objects, such as proteins or molecules, to a … (voir plus)small set of promising candidates with desirable properties. While this process can rely on expert knowledge, recent methods leverage reinforcement learning (RL) guided by a proxy reward function to enable this filtering. By employing various forms of entropy regularization, these methods aim to learn samplers that generate diverse candidates that are highly rated by the proxy function. In this work, we make two main contributions. First, we show that these methods are liable to generate overly diverse, suboptimal candidates in large search spaces. To address this issue, we introduce a novel unified operator that combines several regularized RL operators into a general framework that better targets peakier sampling distributions. Secondly, we offer a novel, robust RL perspective of this filtering process. The regularization can be interpreted as robustness to a compositional form of uncertainty in the proxy function (i.e., the true evaluation of a candidate differs from the proxy's evaluation). Our analysis leads us to a novel, easy-to-use algorithm we name trajectory general mellowmax (TGM): we show it identifies higher quality, diverse candidates than baselines in both synthetic and real-world tasks. Code: https://github.com/marcojira/tgm.

2025-06-19

ArXiv (prépublication)

AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

Andrew Williams

Phillip Wozny

Kai-Hendrik Cohrs

Koen Ponse

Marco Jiralerspong

Soham Phade

Sunil Srinivasa

Lu Li

Yang Zhang

Prateek Gupta

Erman Acar

Irina Rish

Stephan Zheng

Comprehensive global cooperation is essential to limit global temperature increases while continuing economic development, e.g., reducing se… (voir plus)vere inequality or achieving long-term economic growth. Achieving long-term cooperation on climate change mitigation with n strategic agents poses a complex game-theoretic problem. For example, agents may negotiate and reach climate agreements, but there is no central authority to enforce adherence to those agreements. Hence, it is critical to design negotiation and agreement frameworks that foster cooperation, allow all agents to meet their individual policy objectives, and incentivize long-term adherence. This is an interdisciplinary challenge that calls for collaboration between researchers in machine learning, economics, climate science, law, policy, ethics, and other fields. In particular, we argue that machine learning is a critical tool to address the complexity of this domain. To facilitate this research, here we introduce RICE-N, a multi-region integrated assessment model that simulates the global climate and economy, and which can be used to design and evaluate the strategic outcomes for different negotiation and agreement frameworks. We also describe how to use multi-agent reinforcement learning to train rational agents using RICE-N. This framework underpinsAI for Global Climate Cooperation, a working group collaboration and competition on climate negotiation and agreement design. Here, we invite the scientific community to design and evaluate their solutions using RICE-N, machine learning, economic intuition, and other domain knowledge. More information can be found on www.ai4climatecoop.org.

2025-04-30

International Conference on Machine Learning (poster)