Recent advancements in 3D object detection and novel category detection have made significant progress, yet research on learning generalized 3D objectness remains insufficient. In this paper, we delve into learning open-world 3D objectness, which focuses on detecting all objects in a 3D scene, including novel objects unseen during training. Traditional closed-set 3D detectors struggle to generalize to openworld scenarios, while directly incorporating 3D open-vocabulary models for openworld ability struggles with vocabulary expansion and semantic overlap. To achieve generalized 3D object discovery, we propose OP3Det, a class-agnostic OpenWorld Prompt-free 3DDetector to detect any objects within 3D scenes without relying on hand-crafted text prompts. We introduce the strong generalization and zero-shot capabilities of 2D foundation models, utilizing both 2D semantic priors and 3D geometric priors for class-agnostic proposals to broaden 3D object discovery. Then, by integrating complementary information from point cloud and RGB image in the cross-modal mixture of experts, OP3Det dynamically routes uni-modal and multi-modal features to learn generalized 3D objectness. Extensive experiments demonstrate the extraordinary performance of OP3Det, which significantly surpasses existing open-world 3D detectors by up to 16.0% in AR and achieves a 13.5% improvement compared to closed-world 3D detectors.

Emerging reasoning LLMs such as OpenAI-o1 and DeepSeek-R1 have achieved strong performance on complex reasoning tasks by generating long chain-ofthought (CoT) traces. However, these long CoTs result in increased token usage, leading to higher inference latency and memory consumption. As a result, balancing accuracy and reasoning efficiency has become essential for deploying reasoning LLMs in practical applications. Existing long-to-short (Long2Short) methods aim to reduce inference length but often sacrifice accuracy, revealing a need for an approach that maintains performance while lowering token costs. To address this efficiency-accuracy tradeoff, we propose TokenSqueeze, a novel Long2Short method that condenses reasoning paths while preserving performance and relying exclusively on self-generated data. First, to prevent performance degradation caused by excessive compression of reasoning depth, we propose to select self-generated samples whose reasoning depth is adaptively matched to the complexity of the problem. To further optimize the linguistic expression without altering the underlying reasoning paths, we introduce a distribution-aligned linguistic refinement method that enhances the clarity and conciseness of the reasoning path while preserving its logical integrity. Comprehensive experimental results demonstrated the effectiveness of TokenSqueeze in reducing token usage while maintaining accuracy. Notably, DeepSeek-R1-Distill-Qwen-7B fine-tuned by using our proposed method achieved a 50% average token reduction while preserving accuracy on the MATH500 benchmark.

Self-Taught Reasoners (STaR), synonymously known as Rejection sampling FineTuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often employs random observation (data) sampling. However, this results in trained observation imbalance; inefficiently over-training on solved examples while under-training on challenging ones.

The optimal bit-width for achieving the best trade-off between quantized model size and accuracy has been a subject of ongoing debate. While some advocate for 4-bit quantization, others propose that 1.58-bit offers superior results. However, the lack of a cohesive framework for different bits has left such conclusions relatively tenuous.

The data generation process includes situation sampling, long-form text generation, query generation for the long-form text, and QA generation. It is based on human observations of changes, object attributes, and allocentric object relationships in 3DSSG [9], as well as egocentric relationships between the human and the objects. A.1 Situation Sampling We follow the situation categories of MSQA [4], namely sitting, interacting, and standing, but with more detailed geometric analysis: Sitting. The 28seat categories in 3RScan [8] are grouped into four types: 3large seats with backrests (e.g., sofa), 16 small seats with backrests (e.g., armchair), 1 large seat without a backrest (bed), and 8small seats without backrests (e.g., beanbag). Seatable and backrest areas are classified by surface normals, or by nearby walls within 0.5 m if no backrest exists. For small seats, the seating point is the bounding box center, oriented away from the backrest. For large seats, we select a point with a backrest behind and open space (0.5-1 m) in front.

Physical environments and circumstances are fundamentally dynamic, yet current 3D datasets and evaluation benchmarks tend to concentrate on either dynamic scenarios or dynamic situations in isolation, resulting in incomplete comprehension. To overcome these constraints, we introduce Situat3DChange, an extensive dataset supporting three situation-aware change understanding tasks following the perception-action model: 121K question-answer pairs, 36K change descriptions for perception tasks, and 17K rearrangement instructions for the action task. To construct this large-scale dataset, Situat3DChange leverages 11K human observations of environmental changes to establish shared mental models and shared situational awareness for human-AI collaboration. These observations, enriched with egocentric and allocentric perspectives as well as categorical and coordinate spatial relations, are integrated using an LLM to support understanding of situated changes. To address the challenge of comparing pairs of point clouds from the same scene with minor changes, we propose SCReasoner, an efficient 3DMLLM approach that enables effective point cloud comparison with minimal parameter overhead and no additional tokens required for the language decoder. Comprehensive evaluation on Situat3DChange tasks highlights both the progress and limitations of MLLMs in dynamic scene and situation understanding. Additional experiments on data scaling and cross-domain transfer demonstrate the task-agnostic effectiveness of using Situat3DChange as a training dataset for MLLMs.

We find that the cross-entropy loss curves of neural language models empirically adhere to a scaling law with learning rate (LR) annealing over training steps: L(s) = L0 +A S α1 C S2, where L(s)is the validation loss at step s, S1 is the area under the LR curve, S2 is the LR annealing area, and L0, A, C, αare constant parameters.

Self-improvement via RL often fails on complex reasoning tasks because GRPOstyle post-training methods rely on the model's initial ability to generate positive samples. Without guided exploration, these approaches merely reinforce what the model already knows (distribution-sharpening) rather than enabling the model to solve problems where it initially generates no correct solutions. To unlock reasoning ability in such settings, the model must explore new reasoning trajectories beyond its current output distribution. Such exploration requires access to sufficiently good positive samples to guide the learning. While expert demonstrations seem like a natural solution, we find that they are often ineffective in RL post-training.

We introduce MLRC-BENCH, a benchmark designed to quantify how effectively language agents can tackle challenging Machine Learning (ML) Research Competitions, with a focus on open research problems that demand novel methodologies. Unlike prior work, e.g., AIScientist [40], which evaluates the end-to-end agentic pipeline by using LLM-as-a-judge, MLRC-BENCH measures the key steps of proposing and implementing novel research methods and evaluates them with rigorous protocol and objective metrics. Our curated suite of 7 competition tasks reveals significant challenges for LLM agents. Even the best-performing tested agent (gemini-exp-1206 under MLAB [22]) closes only 9.3% of the gap between baseline and top human participant scores. Furthermore, our analysis reveals a misalignment between the LLM-judged innovation and their actual performance on cutting-edge ML research problems. MLRC-BENCH is a dynamic benchmark, which is designed to continually grow with new ML competitions to encourage rigorous and objective evaluations of AI's research capabilities. Our leaderboard and code are publicly available at https://huggingface.co/spaces/launch/MLRC_Bench.

Effective generalization in language models depends critically on the diversity of their training data. Yet existing diversity metrics often fall short of this goal, relying on surface-level heuristics that are decoupled from model behavior. This motivates us to ask: What kind of diversity in training data actually drives generalization in language models--and how can we measure and amplify it? Through largescale empirical analyses spanning over 300 training runs, carefully controlled for data scale and quality, we show that data diversity can be a strong predictor of generalization in LLM reasoning--as measured by average model performance on unseen out-of-distribution benchmarks. We introduce G-Vendi, a metric that quantifies diversity via the entropy of model-induced gradients. Despite using a small off-the-shelf proxy model for gradients, G-Vendi consistently outperforms alternative measures, achieving strong correlation (Spearman's ρ 0.9) with outof-distribution (OOD) performance on both natural language inference (NLI) and math reasoning tasks.