相关论文: CoSPlay: Cooperative Self-Play at Test-Time with S…

Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is…

Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the…

Large language models (LLMs) with a large number of parameters achieve strong performance but are often prohibitively expensive to deploy. Recent work explores using teams of smaller, more efficient LLMs that collectively match or even…

Finding codes given natural language query isb eneficial to the productivity of software developers. Future progress towards better semantic matching between query and code requires richer supervised training resources. To remedy this, we…

Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned…

The increasing demand for spatiotemporal data and modeling tasks in geosciences has made geospatial code generation technology a critical factor in enhancing productivity. Although large language models (LLMs) have demonstrated potential in…

In this paper, we propose a novel co-learning framework (CoSSL) with decoupled representation learning and classifier learning for imbalanced SSL. To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE) for classifier…

Scaling test-time compute has proven highly effective for language models, yet this opportunity remains largely unexplored for industrial Click-Through Rate (CTR) prediction. CTR models suffer from a fundamental asymmetry: feature…

Large language models are increasingly adopted as semantic backbones for neural text-to-speech systems. However, frozen LLM representations are insufficient for modeling speaker specific acoustic and perceptual characteristics. Our…

With the advancement of Large Language Models (LLMs), their application in Software Quality Assurance (SQA) has increased. However, the current focus of these applications is predominantly on ChatGPT. There remains a gap in understanding…

Speech editing and zero-shot Text-to-Speech (TTS) share a similar generative foundation conditioned on speech prompts, yet speech editing demands far stricter local acoustic consistency with surrounding unedited content. While prior work…

Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided self-refinement…

Increasing test-time computation has emerged as a promising direction for improving language model performance, particularly in scenarios where model finetuning is impractical or impossible due to computational constraints or private model…

Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this challenge by generating multiple candidate solutions and…

Reinforcement learning with verifiable rewards (RLVR) plays a crucial role in expanding the capacities of LLM reasoning, but GRPO-style training is dominated by expensive rollouts and wastes compute on unusable prompts. We propose Prompt…

Large language models can generate solutions to complex problems, but training them with reinforcement learning typically requires verifiable rewards that are expensive to create and not possible for all domains. We demonstrate that LLMs…

The rise of Large Language Models (LLMs) has reshaped machine translation (MT), but multilingual MT still relies heavily on parallel data for supervised fine-tuning (SFT), facing challenges like data scarcity for low-resource languages and…

Mainstream issue-resolving frameworks predominantly rely on commercial models, leading to high costs and privacy concerns. Existing training approaches for issue resolving struggle with poor generalization and fail to fully leverage…

Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution space. However, existing parallel TTS methods typically keep branches isolated during…

Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do these approaches…