72 accepted papers
In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)—where coordination with unknown partners is required—remains unexplored. To rigorously evaluate this, we introduce a large-scale benchmark **ICRL4…
Multiple-choice question answering (MCQA) has been a popular format for evaluating and reinforcement fine-tuning (RFT) of modern multimodal language models. Its constrained output format allows for simplified, deterministic automatic verification.However, we find that the options may leak exploitabl
The rapid evolution of Large Language Models (LLMs) has empowered even non-programmers to create visually appealing frontend mini-games with a single instruction. However, open-source models significantly lag behind proprietary counterparts in this domain. The core bottleneck is the lack of an evalu…
Recent diffusion-based Multimodal Large Language Models (dMLLMs) suffer from high inference latency and therefore rely on caching techniques to accelerate decoding. However, the application of cache mechanisms often introduces undesirable repetitive text generation, a phenomenon we term the Repeat C…
How far are deep models from real-world video anomaly understanding (VAU)? Current works typically emphasize detecting unexpected occurrences deviating from normal patterns or comprehending anomalous events with interpretable descriptions. However, they exhibit only a superficial comprehension of re
Instruction-guided image editing has achieved remarkable progress, yet current models still face challenges with complex instructions and often require multiple samples to produce a desired result. Reinforcement Learning (RL) offers a promising solution, but its adoption in image editing has been se…
Accurate scene perception is critical for vision-based robotic manipulation. Existing approaches typically follow either a Vision-to-Action V-A paradigm, predicting actions directly from visual inputs, or a Vision-to-3D-to-Action V-3D-A paradigm, leveraging intermediate 3D representations. However, …
Humor, as both a creative human activity and a social binding mechanism, has long posed a major challenge for AI generation. Although producing humor requires complex cognitive reasoning and social understanding, theories of humor suggest that it follows learnable patterns and structures, making it
Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. Existing benchmarks are usually constructed in a task-oriented manner, without a guarantee…
We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios. We propose a simple yet effective framework based on conditional binary segmentation, where an obje
Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to degraded generalization. Although numerous long-tailed SSL (LTSSL) methods have been proposed, the underlying mechanisms of class bias remain underexpl…
Multimodal generative models can process instructions in various modalities and demonstrate outstanding performance across a wide range of image generation tasks. However, their robustness in complex real-world scenarios remains limited due to insufficient generalized instruction alignment. We intro
Recent Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation. However, their ability to create complex visualizations for scaled and structured data remains largely unevaluated and underdeveloped. To address this gap, we introduce **PlotCraft**, a new benchmark fea…
Recent reinforcement learning (RL) based large-thinking models demonstrate impressive expert-level abilities, i.e., software and math, but still rely heavily on verifiable rewards in specific domains, which places a significant bottleneck to extend the performance boundary of general reasoning capab…
Modern large language models (LLMs) excel at generating fluent and faithful translations. However, they struggle to preserve an author's unique literary style, often producing semantically correct but generic outputs. This limitation stems from the inability of current single-model and static multi-…
Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult tes…
Novel view synthesis of dynamic scenes is fundamental to achieving photorealistic 4D reconstruction and immersive visual experiences. Recent progress in Gaussian-based representations has significantly improved real-time rendering quality, yet existing methods still struggle to maintain a balance be
Multimodal geometry reasoning requires models to jointly understand visual diagrams and perform structured symbolic inference, yet current vision--language models struggle with complex geometric constructions due to limited training data and weak visual--symbolic alignment. We propose a pipeline for…
The growing scale of datasets in deep learning has introduced significant computational challenges. Dataset pruning addresses this challenge by constructing a compact but informative coreset from the full dataset with comparable performance. Previous approaches typically establish scoring metrics ba
Enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) is of great scientific and practical significance. Researchers typically employ process-supervised reward models (PRMs) to guide the reasoning process, effectively improving the models’ reasoning abilities. However, ex…
Remarkable progress on large language models (LLMs), particularly in English, has facilitated impressive capabilities in following human instructions. However, there remains a noticeable gap in instruction fine-tuning for Chinese, where the complex linguistic features pose significant challenges. Ex…
Complex multi-step reasoning remains challenging for large language models (LLMs). While parallel inference-time scaling methods, such as step-level beam search, offer a promising solution, existing approaches typically depend on either domain-specific external verifiers, or self-evaluation which is
Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational costs. Traditional data selection methods often require fin…
Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs causes difficulties for student models to learn. In this paper…
The curse of multilinguality phenomenon is a fundamental problem of multilingual Large Language Models (LLMs), where the competition between massive languages results in inferior performance. It mainly comes from limited capacity and negative transfer between dissimilar languages. To address this is…
Ensembling various LLMs to unlock their complementary potential and leverage their individual strengths is highly valuable. Previous studies typically focus on two main paradigms: sample-level and token-level ensembles. Sample-level ensemble methods either select or blend fully generated outputs, wh…
Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is hampered by data scarcity. To address this, we propose a nove…
Recent advances have demonstrated that integrating reinforcement learning with rule-based rewards can significantly enhance the reasoning capabilities of large language models (LLMs), even without supervised fine-tuning (SFT). However, prevalent reinforcement learning algorithms such as GRPO and its…
Long-context modeling has drawn more and more attention in the area of Large Language Models (LLMs). Continual training with long-context data becomes the de-facto method to equip LLMs with the ability to process long inputs. However, it still remains an open challenge to measure the quality of long…
A core barrier preventing recommender systems from reaching their full potential lies in the inherent limitations of user-item interaction data: (1) Sparse user-item interactions, making it difficult to learn reliable user preferences; (2) Traditional contrastive learning methods often treat negativ
Recent progress in o1-like models has significantly enhanced the reasoning abilities of Large Language Models (LLMs), empowering them to tackle increasingly complex tasks through reflection capabilities, such as making assumptions, backtracking, and self-refinement. However, effectively evaluating s…
Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited "first-class" languages such as English and Chinese, leaving many other languages underrepresented. This imbalance, while limiting broader applicati…
Recent advances in text-only “slow-thinking” reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (VRMs). However, such transfer faces critical challenges: Effective “slow thinking” in VRMs requires visual reflection, the
In this paper, we introduce ManiVideo, a novel method for generating consistent and temporally coherent bimanual hand-object manipulation videos from given motion sequences of hands and objects. The core idea of ManiVideo is the construction of a multi-layer occlusion (MLO) representation that learn…
Traditional recommender systems have relied heavily on positive feedback for learning user preferences, while the abundance of negative feedback in real-world scenarios remains underutilized. To address this limitation, recent years have witnessed increasing attention on leveraging negative feedback…
Recent advancements in large language models (LLMs) with billions of parameters have improved performance in various applications, but their inference processes demand significant energy and computational resources. In contrast, the human brain, with approximately 86 billion neurons, is much more en…
We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD). Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development steps directly from unit tests, which inherently encapsulate…
In visual question answering (VQA) context, users often pose ambiguous questions to visual language models (VLMs) due to varying expression habits. Existing research addresses such ambiguities primarily by rephrasing questions. These approaches neglect the inherently interactive nature of user inter…
Tensegrity structures have been widely explored for their lightweight, high-stiffness, and foldable properties. These unique characteristics have enabled their application in various fields including robotics. Tensegrity robots have demonstrated diverse locomotion modes offering versatile solutions
Tokenization serves as a foundational step for Large Language Models (LLMs) to process text. In new domains or languages, the inefficiency of the tokenizer will slow down the training and generation of LLM. The mismatch in vocabulary also hinders deep knowledge transfer between LLMs like token-level…
The recent release of GPT-4o showcased the potential of end-to-end multimodal models, not just in terms of low latency but also in their ability to understand and generate expressive speech with rich emotions. While the details are unknown to the open research community, it likely involves significa…
Pretrained foundation models offer substantial benefits for a wide range of downstream tasks, which can be one of the most potential techniques to access artificial general intelligence. However, scaling up foundation transformers for maximal task-agnostic knowledge has brought about computational c…
Ensembling different large language models (LLMs) to unleash their complementary potential and harness their individual strengths is highly valuable. Nevertheless, vocabulary discrepancies among various LLMs have constrained previous studies to either selecting or blending completely generated outpu…
The advancement of large language models (LLMs) has enhanced the ability to generalize across a wide range of unseen natural language processing (NLP) tasks through instruction-following.Yet, their effectiveness often diminishes in low-resource languages like Chinese, exacerbated by biased evaluatio…
Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated distributions of multilingual sentence representations, which…
Unsupervised neural machine translation (UNMT) models are trained with pseudo-parallel sentences constructed by on-the-fly back-translation using monolingual corpora. However, the quality of pseudo-parallel sentences cannot be guaranteed, which hinders the final performance of UNMT. This paper demon…
Visual question answering (VQA) tasks, often performed by visual language model (VLM), face challenges with long-tail knowledge. Recent retrieval-augmented VQA (RA-VQA) systems address this by retrieving and integrating external knowledge sources. However, these systems still suffer from redundant v…
Learning-based approaches to monocular motion capture have recently shown promising results by learning to regress in a data-driven manner. However due to the challenges in data collection and network designs it remains challenging to achieve real-time full-body capture while being accurate in world…
Towards energy-efficient artificial intelligence similar to the human brain, the bio-inspired spiking neural networks (SNNs) have advantages of biological plausibility, event-driven sparsity, and binary activation. Recently, large-scale language models exhibit promising generalization capability, ma…
Large language models respond well in high-resource languages like English but struggle in low-resource languages. It may arise from the lack of high-quality instruction following data in these languages. Directly translating English samples into these languages can be a solution but unreliable, lea…
Adapter-tuning inserts simple feed-forward layers (adapters) in pre-trained language models (PLMs) and just tunes the adapters when transferring to downstream tasks, having become the state-of-the-art parameter-efficient tuning (PET) strategy. Although the adapters aim to learn task-related represen…
Fine-tuning all parameters of large language models (LLMs) requires significant computational resources and is time-consuming. Recent parameter-efficient tuning methods such as Adapter tuning, Prefix tuning, and LoRA allow for updating a small subset of parameters in large language models. However,…
Recent studies have revealed the remarkable cross-lingual capability of multilingual pre-trained language models (mPLMs), even when pre-trained without parallel corpora (mono-mPLMs). Intuitively, semantic alignments may be the reason behind such capability but remain under-explored. In this work, we…
Language prompting induces the model to produce a textual output during the training phase, which achieves remarkable performance in few-shot learning scenarios. However, current prompt-based methods either use the same task-specific prompts for each instance, losing the particularity of instance-de…
Multilingual neural machine translation (NMT) enables positive knowledge transfer among multiple translation tasks with a shared underlying model, but a unified multilingual model usually suffers from capacity bottleneck when tens or hundreds of languages are involved. A possible solution is to clus…
Decoding language from non-invasive brain activity has attracted increasing attention from both researchers in neuroscience and natural language processing. Due to the noisy nature of brain recordings, existing work has simplified brain-to-word decoding as a binary classification task which is to di…
End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST data, which are difficult and expensive to obtain. Fortunately, the superv…
Confidence estimation aims to quantify the confidence of the model prediction, providing an expectation of success. A well-calibrated confidence estimate enables accurate failure prediction and proper risk measurement when given noisy samples and out-of-distribution data in real-world settings. Howe…
Recent advances in neural machine translation depend on massive parallel corpora, which are collected from any open source without much guarantee of quality. It stresses the need for noisy corpora filtering, but existing methods are insufficient to solve this issue. They spend much time ensembling m…
Role-oriented dialogue summarization is to generate summaries for different roles in the dialogue, e.g., merchants and consumers. Existing methods handle this task by summarizing each role’s content separately and thus are prone to ignore the information from other roles. However, we believe that ot…
Multilingual neural machine translation (MNMT) aims to translate multiple languages with a single model and has been proved successful thanks to effective knowledge transfer among different languages with shared parameters. However, it is still an open question which parameters should be shared and…
Neuroimaging studies have identified multiple brain regions that are associated with semantic and syntactic processing when comprehending language. However, existing methods cannot explore the neural correlates of fine-grained word syntactic features, such as part-of-speech and dependency relations.…
Attention mechanisms have achieved substantial improvements in neural machine translation by dynamically selecting relevant inputs for different predictions. However, recent studies have questioned the attention mechanisms’ capability for discovering decisive inputs. In this paper, we propose to cal…
Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the token imbalance problem. However, previous approaches only use s…
Dialogue summarization has drawn much attention recently. Especially in the customer service domain, agents could use dialogue summaries to help boost their works by quickly knowing customer’s issues and service progress. These applications require summaries to contain the perspective of a single sp…
Multi-modal machine translation (MMT) aims at improving translation performance by incorporating visual information. Most of the studies leverage the visual information through integrating the global image features as auxiliary input or decoding by attending to relevant local regions of the image. H…
Back-translation (BT) has become one of the de facto components in unsupervised neural machine translation (UNMT), and it explicitly makes UNMT have translation ability. However, all the pseudo bi-texts generated by BT are treated equally as clean data during optimization without considering the qua…
To simultaneously translate a source language into multiple different target languages is one of the most common scenarios of multilingual translation. However, existing methods cannot make full use of translation model information during decoding, such as intra-lingual and inter-lingual future info…
Accumulating knowledge to tackle new tasks without necessarily forgetting the old ones is a hallmark of human-like intelligence. But the current dominant paradigm of machine learning is still to train a model that works well on static datasets. When learning tasks in a stream where data distribution…
Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized. ii) Granularity mismat…
Knowledge graphs (KGs) store much structured information on various entities, many of which are not covered by the parallel sentence pairs of neural machine translation (NMT). To improve the translation quality of these entities, in this paper we propose a novel KGs enhanced NMT method. Specificall…
This paper studies the problem of generating a summary for a given sentence-image pair. Existing multimodal sequence-to-sequence approaches mainly focus on enhancing the decoder by visual signals, while ignoring that the image can improve the ability of the encoder to identify highlights of a news e…