Related papers: Recon: Reconstruction-Guided Reasoning Synthesis f…

Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, these intermediate inference steps may be inappropriate…

Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step…

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection…

Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternatives (interventions), and predicting their outcomes (prediction). This skill is…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Referring expression comprehension (REF) aims at identifying a particular object in a scene by a natural language expression. It requires joint reasoning over the textual and visual domains to solve the problem. Some popular referring…

Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning, its verbosity imposes substantial computational overhead.…

Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning its predictions should be both explainable and faithful to…

Recommender systems, while a powerful decision making tool, are often operationalized as black box models, such that their AI algorithms are not accessible or interpretable by human operators. This in turn can cause confusion and…

We present a model for pragmatically describing scenes, in which contrastive behavior results from a combination of inference-driven pragmatics and learned semantics. Like previous learned approaches to language generation, our model uses a…

Search-based recommendation is one of the most critical application scenarios in e-commerce platforms. Users' complex search contexts--such as spatiotemporal factors, historical interactions, and current query's information--constitute an…

Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To address this, we introduce Behavior Cue Reasoning for making LLM reasoning more controllable…

Large language models show improved downstream task performance when prompted to generate step-by-step reasoning to justify their final answers. These reasoning steps greatly improve model interpretability and verification, but objectively…

The underperformance of existing multimodal large language models for time series reasoning lies in the absence of rationale priors that connect temporal observations to their downstream outcomes, which leads models to rely on superficial…

Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…

While reasoning models (e.g., DeepSeek R1) trained with reinforcement learning (RL), excel in textual reasoning, they struggle in scenarios requiring structured problem-solving, such as geometric reasoning, concise computation, or complex…

Recent advances in long chain-of-thought (CoT) reasoning have largely prioritized answer accuracy and token efficiency, while overlooking aspects critical to trustworthiness. We argue that usable reasoning systems must be trustworthy,…

Programming-by-example is the task of synthesizing a program that is consistent with a set of user-provided input-output examples. As examples are often an under-specification of one's intent, a good synthesizer must choose the intended…

Recent advances in sparse reward policy gradient methods have enabled effective reinforcement learning (RL)-based language model post-training. However, for reasoning tasks such as mathematical problem solving, binarized outcome rewards…

Human action recognition has drawn a lot of attention in the recent years due to the research and application significance. Most existing works on action recognition focus on learning effective spatial-temporal features from videos, but…