Samsung Galaxy Unpacked 2026 is Feb. 25 Valve's Steam Machine: Everything we know Plus, a tactical shooter from the team behind Half-Life remake Black Mesa. Welcome to our latest roundup of what's going on in the indie game space. A whole bunch of compelling games arrived this week, and Sony dropped some news about more that are on the way to PS5 and other platforms during its State of Play stream on Thursday . For one thing, I didn't have a prequel for, one of my favorite games of the last few years on my bingo card. It's really neat that Motion Twin and Evil Empire -- the studios behind and its expansions, respectively -- are getting to make a proper Castlevania game .

Accurate motion forecasting for traffic agents is crucial for ensuring the safety and efficiency of autonomous driving systems in dynamically changing environments. Mainstream methods adopt a one-query-one-trajectory paradigm, where each query corresponds to a unique trajectory for predicting multi-modal trajectories. While straightforward and effective, the absence of detailed representation of future trajectories may yield suboptimal outcomes, given that the agent states dynamically evolve over time. To address this problem, we introduce DeMo, a framework that decouples multi-modal trajectory queries into two types: mode queries capturing distinct directional intentions and state queries tracking the agent's dynamic states over time.

Li Zhang (lizhangfd@fudan.edu.cn) is the corresponding author. Previous methods, as depicted in (a), use only one mode query for each trajectory.

Additionally, MBD's ability to integrate with data enhances its versatility and

We thank all reviewers for their constructive comments and are glad that our contributions are largely recognized. Below, we address the reviewer's concerns point by point. A, we provide results of three MuJoCo manipulation examples: Pusher, Striker and Thrower . GAIL and GAIfO, our method is able to outperform all other LfO baselines. We thank the reviewer for the reminding.

We sincerely thank the reviewers for their helpful comments. The baselines do not solve BiMGame & AntMaze even with optimal trajectories. Fig. D, E shows this as We see similar trends for AggreV aTeD. Although they stagnate after making some progress, their cumulative terminal-only reward is 0. (see Line 300-302). We only assume ordering of state groups, which is implicit in many tasks.

Detecting Alzheimer's disease (AD) from narrative transcripts challenges large language models (LLMs): pre-training rarely covers this out-of-distribution task, and all transcript demos describe the same scene, producing highly homogeneous contexts. These factors cripple both the model's built-in task knowledge (\textbf{task cognition}) and its ability to surface subtle, class-discriminative cues (\textbf{contextual perception}). Because cognition is fixed after pre-training, improving in-context learning (ICL) for AD detection hinges on enriching perception through better demonstration (demo) sets. We demonstrate that standard ICL quickly saturates, its demos lack diversity (context width) and fail to convey fine-grained signals (context depth), and that recent task vector (TV) approaches improve broad task adaptation by injecting TV into the LLMs' hidden states (HSs), they are ill-suited for AD detection due to the mismatch of injection granularity, strength and position. To address these bottlenecks, we introduce \textbf{DA4ICL}, a demo-centric anchoring framework that jointly expands context width via \emph{\textbf{Diverse and Contrastive Retrieval}} (DCR) and deepens each demo's signal via \emph{\textbf{Projected Vector Anchoring}} (PVA) at every Transformer layer. Across three AD benchmarks, DA4ICL achieves large, stable gains over both ICL and TV baselines, charting a new paradigm for fine-grained, OOD and low-resource LLM adaptation.

Communication-efficient distributed training algorithms have received considerable interest recently due to their benefits for training Large Language Models (LLMs) in bandwidth-constrained settings, such as across datacenters and over the internet. Despite reducing communication frequency, these methods still typically require communicating a full copy of the model's gradients-resulting in a communication bottleneck even for cross-datacenter links. Furthermore, they can slightly degrade performance compared to a naive AdamW DDP baseline. While quantization is often applied to reduce the pseudo-gradient's size, in the context of LLM pre-training, existing approaches have been unable to additionally leverage sparsification and have obtained limited quantization. In this work, we introduce SparseLoCo, a communication-efficient training algorithm for LLMs that effectively leverages error feedback with Top-k sparsification and 2-bit quantization to reach extreme sparsity as low as 1-3% while outperforming full-precision DiLoCo. Our key observations are that outer momentum can be locally approximated by an error feedback accumulator combined with aggressive sparsity, and that sparse aggregation can actually improve model performance. We empirically demonstrate in a range of communication-constrained LLM training settings that SparseLoCo provides significant benefits in both performance and communication cost.

Audio-driven talking-head generation has advanced rapidly with diffusion-based generative models, yet producing temporally coherent videos with fine-grained motion control remains challenging. We propose DEMO, a flow-matching generative framework for audio-driven talking-portrait video synthesis that delivers disentangled, high-fidelity control of lip motion, head pose, and eye gaze. The core contribution is a motion auto-encoder that builds a structured latent space in which motion factors are independently represented and approximately orthogonalized. On this disentangled motion space, we apply optimal-transport-based flow matching with a transformer predictor to generate temporally smooth motion trajectories conditioned on audio. Extensive experiments across multiple benchmarks show that DEMO outperforms prior methods in video realism, lip-audio synchronization, and motion fidelity. These results demonstrate that combining fine-grained motion disentanglement with flow-based generative modeling provides a powerful new paradigm for controllable talking-head video synthesis.

Li Zhang (lizhangfd@fudan.edu.cn) is the corresponding author. Previous methods, as depicted in (a), use only one mode query for each trajectory.